OnDevice: Local AI Studio

• A simpler app design and a redesigned model library. • Switch between My Models and Discover, with clearer filters and focused model details. • A refined composer with more room to write and clearer model and attachment controls. • Improved interface translations across all 15 supported languages, including Turkish, and right-to-left layouts for Arabic. • Better readability and navigation at larger text sizes.

A clearer local API workspace • Open Local API Server directly from the Studio home screen. • A dedicated Local API Server page with separate server and model status. • Start, stop, or restart the server and load installed local models without automatic downloads. • Copy pinned HTTPS setup commands for OpenAI, Anthropic, and Ollama clients. • Confirm API key rotation, hide revealed keys when leaving the page or backgrounding, and save validated port changes. • Improved dark mode and large-text layouts.

NEW • Attached images now work with every assistant model. Multimodal models read pixels directly; text-only models use the bundled SmolVLM2-500M on-device visual bridge. • Added persistent per-model generation settings, while app defaults remain the starting point. • Added an explicit default assistant model. New chats use it, while each existing conversation remembers its own selected model. • Added whole-conversation sharing with a clean chronological transcript. • Assistant replies now show tokens/second and generation time with clear icons. IMPROVED • Fixed the keyboard-open composer conflict: completed answers no longer show through the input controls, and the text field is clearly separated from the action row. • Fixed conversation model switching reverting to the saved default instead of loading the model selected for that conversation. • Fixed valid community models such as Jackrong Qwen3.5 appearing in the chat picker but missing from the Models tab and Downloaded-only inventory. • Fixed Local API requests from browsers and agent clients getting stuck at “Generating.” Web preflight, streaming event framing, graceful completion, and tool-call decision timing are now handled correctly. • Conversation model switching now shows every valid downloaded assistant and links to Models when none are installed. • Expanded completed-response spacing repair for image descriptions and product details. • Fixed a case where a text-only model could show a blank answer immediately after SmolVLM2 analyzed an attached image. • The composer hides while a reply is generating and returns without covering the completed answer, footer, or quick actions. • Completed replies keep compact typography and clearer Markdown spacing. • Reasoning streams live again while supported models are thinking. • Long tool cards remain bounded and no longer make the conversation disappear. • Conversation context is preserved more reliably across short follow-up replies. Everything continues to run privately on your device.