From b00c3f9ab31b6836c1ae8336db9b42463906de8b Mon Sep 17 00:00:00 2001 From: Thorsten Sommer Date: Mon, 31 Aug 2026 10:00:09 +0200 Subject: [PATCH] Prepared release v26.8.2 (#946) --- .../Components/Changelog.Logs.cs | 1 + .../wwwroot/changelog/v26.8.2.md | 11 ++--- .../wwwroot/changelog/v26.9.1.md | 1 + metadata.txt | 10 ++--- runtime/Cargo.lock | 2 +- runtime/Cargo.toml | 4 +- .../org.mindworkai.AIStudio.metainfo.xml | 42 +++++++++++++++++++ runtime/tauri.conf.json | 2 +- 8 files changed, 59 insertions(+), 14 deletions(-) create mode 100644 app/MindWork AI Studio/wwwroot/changelog/v26.9.1.md diff --git a/app/MindWork AI Studio/Components/Changelog.Logs.cs b/app/MindWork AI Studio/Components/Changelog.Logs.cs index fc45317b..f10ce907 100644 --- a/app/MindWork AI Studio/Components/Changelog.Logs.cs +++ b/app/MindWork AI Studio/Components/Changelog.Logs.cs @@ -13,6 +13,7 @@ public partial class Changelog public static readonly Log[] LOGS = [ + new (255, "v26.8.2, build 255 (2026-08-31 07:45 UTC)", "v26.8.2.md"), new (254, "v26.8.1, build 254 (2026-08-19 09:35 UTC)", "v26.8.1.md"), new (250, "v26.7.3, build 250 (2026-07-21 12:45 UTC)", "v26.7.3.md"), new (244, "v26.7.2, build 244 (2026-07-06 18:35 UTC)", "v26.7.2.md"), diff --git a/app/MindWork AI Studio/wwwroot/changelog/v26.8.2.md b/app/MindWork AI Studio/wwwroot/changelog/v26.8.2.md index 0fc7e153..7f934020 100644 --- a/app/MindWork AI Studio/wwwroot/changelog/v26.8.2.md +++ b/app/MindWork AI Studio/wwwroot/changelog/v26.8.2.md @@ -1,15 +1,15 @@ -# v26.8.2, build 255 (2026-08-xx xx:xx UTC) +# v26.8.2, build 255 (2026-08-31 07:45 UTC) - Added protection against prompt injection. Documents, web pages, and retrieved content can carry instructions written for the AI rather than for you, for example, text telling it to ignore its rules or to hand over its instructions. AI Studio now always removes such passages before the content reaches a model, while the rest of your document stays intact and usable. When something was removed, AI Studio tells you and can show you which passages it took out. You can turn off the detailed dialog in the app settings. For IT departments: the new setting `DataApp.ShowPromptInjectionAlert` lets you configure the detailed dialog for your organization. Many thanks to Sabrina `Sabrina-devops` for implementing this feature and to Simon `SimonBpunkt` for his work on the detection patterns and their translations. - Added configurable direct-chat launchers for assistant plugins. Plugin authors and the Assistant Builder can now open a chat with a chosen workspace, provider, profile, chat template, and data sources, while unavailable or unauthorized selections are reported before a chat is created. - Added the option to load the assistant description from a file in the Assistant Builder. - Added provider logos throughout AI Studio, making models easier to recognize at a glance. Configuration plugins can now give managed LLM, transcription, and embedding providers their own project icon with the optional `IconPath` field. -- Added the option for IT departments to enable assistant plugins they rolled out. Approving an assistant only stated that it is safe, so everybody still had to switch it on themselves. An approval can now also enable the assistant, either as a default which you may switch off again, or in a way your IT department keeps in place. The plugin page and the security card of the assistant tell you which of the two applies. +- Added the option for IT departments to enable assistant plugins they rolled out. Approving an assistant only stated that it is safe, so everybody still had to switch it on themselves. An approval can now also enable the assistant, either as a default, which you may switch off again, or in a way your IT department keeps in place. The plugin page and the security card of the assistant tell you which of the two applies. - Added knowledge about the latest AI models. AI Studio now recognizes Qwen 3.8 Flash, GLM-5.3 Flash, Meta's Muse Glimmer, NVIDIA's Nemotron 3.5, Tencent's Hunyuan Hy3, Grok 4, Claude Opus 5 and Sonnet 5, and Gemini 3.6 and 3.7. It knows what each of them is capable of, so images, videos, tool usage, and reasoning are available right away instead of staying hidden. - Added the IONOS AI Model Hub as a provider for chats and embeddings. It runs open-source models in Germany, is subject to the GDPR, and IONOS states that your data is not used for training. - Added LiteLLM as a new LLM provider for chats, embeddings, and speech-to-text. LiteLLM is an AI gateway you run yourself in front of models from many providers. Because your gateway decides where your data goes, you set its trust level yourself. Thanks Prodman Devokadev (`prodmanpd`) for this first contribution. - Added speech-to-text for Helmholtz Blablador and GroqCloud, and embeddings for GWDG SAIA. These providers offer these services now, so you can select them when you dictate a message or when you set up a data source. - Added embeddings and speech-to-text for Hugging Face, so you can now use it to prepare your own documents for retrieval and to dictate your messages. Hugging Face offers both through a few of its inference providers only, which is why you get a shorter list to choose from there than you do for chatting. -- Added a model list for Hugging Face. Until now you had to type the name of the model yourself and hope you got it right, down to its capitalization. AI Studio now loads the models your chosen inference provider actually offers, so you pick one from a list and cannot end up with a model that provider does not serve. +- Added a model list for Hugging Face. Until now, you had to type the name of the model yourself and hope you got it right, down to its capitalization. AI Studio now loads the models your chosen inference provider actually offers, so you pick one from a list and cannot end up with a model that the provider does not serve. - Added more file formats for exporting an AI answer. The export button used to offer Microsoft Word only; it is now a menu which also writes OpenDocument Text for LibreOffice, LaTeX, Markdown, and a webpage. When an answer contains tables, each of them can be saved on its own as a spreadsheet file, named after the heading above it and ready to open in Excel or LibreOffice Calc. This works in the chat and for the results of every assistant. Many thanks to Nils Kruthoff (`nilskruthoff`) for this contribution. - Added a choice of file format to the Batch Processing assistant. When it writes one result file per document, those files were always Markdown; you can now pick Microsoft Word, OpenDocument Text, LaTeX, or a webpage instead. For IT departments: the new setting `DataBatchProcessing.ResultFileFormat` lets you configure the format for your organization. - Improved the safety of plugin symbols: AI Studio now shows the symbol of a plugin in isolation, so nothing inside a symbol can reach the rest of the app. @@ -20,7 +20,7 @@ - Improved which models you get to choose from when chatting: models you cannot chat with are now hidden. This is most noticeable with a gateway such as LiteLLM, which offers you everything its providers have, including video, live speech, and audio models. - Changed the model list of GroqCloud. Models which cannot be used for chatting, such as the speech and the safety models, no longer show up among the chat models. The speech models now appear where they belong, in the settings for speech-to-text. - Changed how plugins your organization rolled out are protected. They can no longer be deleted or edited in AI Studio, which already applied to sharing and replacing them. This also covers plugins staged for a test: such a test now ends by restarting AI Studio or by removing the staged files, instead of through the plugin page. -- Fixed the Hugging Face provider, which had stopped working. Hugging Face changed the way requests are addressed, and AI Studio still used the old way, so chatting failed with a puzzling error about the message format. Chatting works again, and you can now reach far more inference providers, among them Z.ai, Groq, Cohere, DeepInfra, and Baseten. You may also leave the choice to Hugging Face and let it pick the fastest or the cheapest provider for you, which switches to another one when your first choice is unavailable. Should a provider not offer the model you selected, AI Studio now tells you so in plain words instead of reporting a technical problem. The providers Hugging Face no longer runs are gone from the list; if you had picked one of them, AI Studio asks you to choose again. +- Fixed the Hugging Face provider, which had stopped working. Hugging Face changed the way requests are addressed, and AI Studio still used the old way, so chatting failed with a puzzling error about the message format. Chatting works again, and you can now reach far more inference providers, among them Z.ai, Groq, Cohere, DeepInfra, and Baseten. You may also leave the choice to Hugging Face and let it pick the fastest or the cheapest provider for you, which switches to another one when your first choice is unavailable. Should a provider not offer the model you selected, AI Studio now tells you so in plain words instead of reporting a technical problem. The providers Hugging Face no longer run are gone from the list; if you had picked one of them, AI Studio asks you to choose again. - Fixed the abilities shown for Google's Gemma models. AI Studio did not recognize them at all and treated every one of them as a text-only model, so images, reasoning, and tool usage stayed hidden even though Gemma 4 handles all three. - Fixed assistants created by the Assistant Builder being named after an internal placeholder, such as "Model decides", when you left the display name empty. The model now picks a fitting name instead. - Fixed AI Studio reading a document to the end even after you closed its preview. Closing the dialog now stops that work immediately. @@ -33,4 +33,5 @@ - Fixed a misleading warning in the log when an organization deployed an archive that carries no configuration of its own. - Fixed AI Studio underrating what many models can do. Newer Claude, Gemini, Grok, DeepSeek, and Qwen models were missing abilities they actually have, such as image input or tool usage. This was most noticeable with OpenRouter, where nearly every model was affected. AI Studio now derives these abilities from the same source for all providers, so a model offers the same capabilities no matter which way you reach it. - Fixed the abilities shown for the models offered by Mistral. Mistral names its models after their release date, so almost every one of them was missing image input or reasoning: picking Mistral Large from the list gave you a different set of abilities than picking the very same model by its full name. AI Studio now goes by the release date and gets all of them right, including the Ministral models and the open-source models Mistral hosts, such as GLM. -- Fixed AI Studio staying silent about why dictating or an embedding failed. When a provider explains what went wrong, you now get to read it instead of a general note that something did not work. If a provider cannot handle the audio format AI Studio sends, it says so and suggests contacting that provider. \ No newline at end of file +- Fixed AI Studio staying silent about why dictating or embedding failed. When a provider explains what went wrong, you now get to read it instead of a general note that something did not work. If a provider cannot handle the audio format AI Studio sends, it says so and suggests contacting that provider. +- Upgraded Rust to v1.98.0 \ No newline at end of file diff --git a/app/MindWork AI Studio/wwwroot/changelog/v26.9.1.md b/app/MindWork AI Studio/wwwroot/changelog/v26.9.1.md new file mode 100644 index 00000000..6fae5e76 --- /dev/null +++ b/app/MindWork AI Studio/wwwroot/changelog/v26.9.1.md @@ -0,0 +1 @@ +# v26.9.1, build 256 (2026-09-xx xx:xx UTC) diff --git a/metadata.txt b/metadata.txt index 421260b1..1033f67e 100644 --- a/metadata.txt +++ b/metadata.txt @@ -1,12 +1,12 @@ -26.8.1 -2026-08-19 09:35:26 UTC -254 +26.8.2 +2026-08-31 07:45:20 UTC +255 9.0.120 (commit 3f97250e38) 9.0.19 (commit 8381bdb01f) -1.97.1 (commit 8bab26f4f) +1.98.0 (commit 88d9e12ae) 8.15.0 2.11.5 -1aed0f8e19b, release +3c18a7bfdb3, release osx-arm64 148.0.7763.0 0.7.2 \ No newline at end of file diff --git a/runtime/Cargo.lock b/runtime/Cargo.lock index 0ae697db..81431e5b 100644 --- a/runtime/Cargo.lock +++ b/runtime/Cargo.lock @@ -4260,7 +4260,7 @@ checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a" [[package]] name = "mindwork-ai-studio" -version = "26.8.1" +version = "26.8.2" dependencies = [ "aes 0.9.1", "aho-corasick", diff --git a/runtime/Cargo.toml b/runtime/Cargo.toml index a5327ea6..9a1a648b 100644 --- a/runtime/Cargo.toml +++ b/runtime/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "mindwork-ai-studio" -version = "26.8.1" +version = "26.8.2" edition = "2024" description = "MindWork AI Studio" authors = ["Thorsten Sommer"] @@ -74,7 +74,7 @@ qdrant-edge = "0.7.2" # phrases in one pass no matter how long that list grows. regex = "1.13.1" aho-corasick = "1.1.5" -toml = "1.1.4+spec-1.1.0" +toml = "1.1.4" image = { version = "0.25.10", default-features = false, features = ["jpeg", "png", "webp"] } [patch.crates-io] diff --git a/runtime/packaging/linux/org.mindworkai.AIStudio.metainfo.xml b/runtime/packaging/linux/org.mindworkai.AIStudio.metainfo.xml index c2ed6a45..e8e9fc05 100644 --- a/runtime/packaging/linux/org.mindworkai.AIStudio.metainfo.xml +++ b/runtime/packaging/linux/org.mindworkai.AIStudio.metainfo.xml @@ -102,6 +102,48 @@ + + +
    +
  • Added protection against prompt injection. Documents, web pages, and retrieved content can carry instructions written for the AI rather than for you, for example, text telling it to ignore its rules or to hand over its instructions. AI Studio now always removes such passages before the content reaches a model, while the rest of your document stays intact and usable. When something was removed, AI Studio tells you and can show you which passages it took out. You can turn off the detailed dialog in the app settings. For IT departments: the new setting DataApp.ShowPromptInjectionAlert lets you configure the detailed dialog for your organization. Many thanks to Sabrina Sabrina-devops for implementing this feature and to Simon SimonBpunkt for his work on the detection patterns and their translations.
    • +
  • Added configurable direct-chat launchers for assistant plugins. Plugin authors and the Assistant Builder can now open a chat with a chosen workspace, provider, profile, chat template, and data sources, while unavailable or unauthorized selections are reported before a chat is created.
    • +
  • Added the option to load the assistant description from a file in the Assistant Builder.
    • +
  • Added provider logos throughout AI Studio, making models easier to recognize at a glance. Configuration plugins can now give managed LLM, transcription, and embedding providers their own project icon with the optional IconPath field.
    • +
  • Added the option for IT departments to enable assistant plugins they rolled out. Approving an assistant only stated that it is safe, so everybody still had to switch it on themselves. An approval can now also enable the assistant, either as a default, which you may switch off again, or in a way your IT department keeps in place. The plugin page and the security card of the assistant tell you which of the two applies.
    • +
  • Added knowledge about the latest AI models. AI Studio now recognizes Qwen 3.8 Flash, GLM-5.3 Flash, Meta's Muse Glimmer, NVIDIA's Nemotron 3.5, Tencent's Hunyuan Hy3, Grok 4, Claude Opus 5 and Sonnet 5, and Gemini 3.6 and 3.7. It knows what each of them is capable of, so images, videos, tool usage, and reasoning are available right away instead of staying hidden.
    • +
  • Added the IONOS AI Model Hub as a provider for chats and embeddings. It runs open-source models in Germany, is subject to the GDPR, and IONOS states that your data is not used for training.
    • +
  • Added LiteLLM as a new LLM provider for chats, embeddings, and speech-to-text. LiteLLM is an AI gateway you run yourself in front of models from many providers. Because your gateway decides where your data goes, you set its trust level yourself. Thanks Prodman Devokadev (prodmanpd) for this first contribution.
    • +
  • Added speech-to-text for Helmholtz Blablador and GroqCloud, and embeddings for GWDG SAIA. These providers offer these services now, so you can select them when you dictate a message or when you set up a data source.
    • +
  • Added embeddings and speech-to-text for Hugging Face, so you can now use it to prepare your own documents for retrieval and to dictate your messages. Hugging Face offers both through a few of its inference providers only, which is why you get a shorter list to choose from there than you do for chatting.
    • +
  • Added a model list for Hugging Face. Until now, you had to type the name of the model yourself and hope you got it right, down to its capitalization. AI Studio now loads the models your chosen inference provider actually offers, so you pick one from a list and cannot end up with a model that the provider does not serve.
    • +
  • Added more file formats for exporting an AI answer. The export button used to offer Microsoft Word only; it is now a menu which also writes OpenDocument Text for LibreOffice, LaTeX, Markdown, and a webpage. When an answer contains tables, each of them can be saved on its own as a spreadsheet file, named after the heading above it and ready to open in Excel or LibreOffice Calc. This works in the chat and for the results of every assistant. Many thanks to Nils Kruthoff (nilskruthoff) for this contribution.
    • +
  • Added a choice of file format to the Batch Processing assistant. When it writes one result file per document, those files were always Markdown; you can now pick Microsoft Word, OpenDocument Text, LaTeX, or a webpage instead. For IT departments: the new setting DataBatchProcessing.ResultFileFormat lets you configure the format for your organization.
    • +
  • Improved the safety of plugin symbols: AI Studio now shows the symbol of a plugin in isolation, so nothing inside a symbol can reach the rest of the app.
    • +
  • Improved how much memory AI Studio needs. Working with large documents used to grow the app to several gigabytes, and on macOS that memory was never handed back. AI Studio now stays at a fraction of that and returns memory to your system. This matters most on devices with little memory, such as a Raspberry Pi.
    • +
  • Improved the preview for large documents. It now shows you the beginning of your document instead of loading all of it, so the dialog opens right away. Your complete document still goes to the AI.
    • +
  • Improved how AI Studio deals with rare internal hiccups. When the app window reloads, or when it briefly loses the connection to its own user interface, work which was still running in the background is now ended properly instead of leaving errors behind.
    • +
  • Improved how IT departments roll plugins out. A configuration server can deliver any kind of plugin, not only configurations: one archive may carry assistant plugins and further types alongside a configuration, each in its own folder. The folder for staging a test behaves the same way, so a test can mirror the later rollout exactly. The Enterprise IT documentation describes the whole procedure.
    • +
  • Improved which models you get to choose from when chatting: models you cannot chat with are now hidden. This is most noticeable with a gateway such as LiteLLM, which offers you everything its providers have, including video, live speech, and audio models.
    • +
  • Changed the model list of GroqCloud. Models which cannot be used for chatting, such as the speech and the safety models, no longer show up among the chat models. The speech models now appear where they belong, in the settings for speech-to-text.
    • +
  • Changed how plugins your organization rolled out are protected. They can no longer be deleted or edited in AI Studio, which already applied to sharing and replacing them. This also covers plugins staged for a test: such a test now ends by restarting AI Studio or by removing the staged files, instead of through the plugin page.
    • +
  • Fixed the Hugging Face provider, which had stopped working. Hugging Face changed the way requests are addressed, and AI Studio still used the old way, so chatting failed with a puzzling error about the message format. Chatting works again, and you can now reach far more inference providers, among them Z.ai, Groq, Cohere, DeepInfra, and Baseten. You may also leave the choice to Hugging Face and let it pick the fastest or the cheapest provider for you, which switches to another one when your first choice is unavailable. Should a provider not offer the model you selected, AI Studio now tells you so in plain words instead of reporting a technical problem. The providers Hugging Face no longer run are gone from the list; if you had picked one of them, AI Studio asks you to choose again.
    • +
  • Fixed the abilities shown for Google's Gemma models. AI Studio did not recognize them at all and treated every one of them as a text-only model, so images, reasoning, and tool usage stayed hidden even though Gemma 4 handles all three.
    • +
  • Fixed assistants created by the Assistant Builder being named after an internal placeholder, such as "Model decides", when you left the display name empty. The model now picks a fitting name instead.
    • +
  • Fixed AI Studio reading a document to the end even after you closed its preview. Closing the dialog now stops that work immediately.
    • +
  • Fixed AI Studio holding on to finished chats, presentation images, and plugin data. It releases them now, so memory no longer grows the longer you keep the app running.
    • +
  • Fixed assistants handing an outdated result to the chat. When you sent several results without opening the chat in between, you now receive the one you sent last.
    • +
  • Fixed rare issues when multiple configurations provided introduction texts or mandatory information under the same ID.
    • +
  • Fixed the description of the global voice recording shortcut always appearing in English. On Linux, your desktop asks you to confirm such a shortcut and shows this description; it now appears in your language.
    • +
  • Fixed the code editor being offered for assistant plugins your organization manages. Editing one would have withdrawn the approval of your IT department and demanded a fresh security audit.
    • +
  • Fixed assistant plugins your organization deployed alongside a configuration not being recognized as centrally managed unless they declared it themselves.
    • +
  • Fixed a misleading warning in the log when an organization deployed an archive that carries no configuration of its own.
    • +
  • Fixed AI Studio underrating what many models can do. Newer Claude, Gemini, Grok, DeepSeek, and Qwen models were missing abilities they actually have, such as image input or tool usage. This was most noticeable with OpenRouter, where nearly every model was affected. AI Studio now derives these abilities from the same source for all providers, so a model offers the same capabilities no matter which way you reach it.
    • +
  • Fixed the abilities shown for the models offered by Mistral. Mistral names its models after their release date, so almost every one of them was missing image input or reasoning: picking Mistral Large from the list gave you a different set of abilities than picking the very same model by its full name. AI Studio now goes by the release date and gets all of them right, including the Ministral models and the open-source models Mistral hosts, such as GLM.
    • +
  • Fixed AI Studio staying silent about why dictating or embedding failed. When a provider explains what went wrong, you now get to read it instead of a general note that something did not work. If a provider cannot handle the audio format AI Studio sends, it says so and suggests contacting that provider.
    • +
  • Upgraded Rust to v1.98.0
    • +
+ +
    diff --git a/runtime/tauri.conf.json b/runtime/tauri.conf.json index 3d9cac39..2587bcfb 100644 --- a/runtime/tauri.conf.json +++ b/runtime/tauri.conf.json @@ -1,7 +1,7 @@ { "productName": "MindWork AI Studio", "mainBinaryName": "MindWork AI Studio", - "version": "26.8.1", + "version": "26.8.2", "identifier": "com.github.mindwork-ai.ai-studio", "build": {