Hovering a reaction in a channel stopped naming the people who reacted and only showed a count, such as "2 🚀". It names them again, for example "You and Alice reacted with 🚀". Reactions on comments keep showing just the count, since the app does not list who reacted there.
Fixes#33392
With native function calling, each model turn that calls tools counts as one iteration, and a single response was stopped with "Tool-call limit reached (256 iterations)." after 256 of them. The CHAT_RESPONSE_MAX_TOOL_CALL_ITERATIONS environment variable now defaults to 1024, also when it is set empty or to something that is not a number, and the error shows the new number. A model stuck calling tools in a loop now runs up to 1024 iterations before it is stopped; setting the variable to 256 keeps the old limit, and -1 still means no limit.
Renaming a chat from the top bar had no way to generate a title, while the sidebar rename has a sparkle button for it. The rename field in the top bar now has the same button: it generates a title from the conversation and saves it right away, like the sidebar does. If you switch chats while the title is generating, it still goes to the original chat and does not show up on the one you switched to.
New **pt-BR** translations for items introduced in the latest releases, plus a consistency/quality pass across existing strings (grammar, tone, capitalization, pluralization). Placeholders and hotkeys preserved. No logic changes.
Menus only let the arrow keys, Home and End reach the entries that were there the moment they opened. Entries that show up afterwards, such as the file, note, knowledge and chat lists in the message box's More menu or the tags in the chat actions menu, could only be reached with Tab or the mouse. These entries can now be reached with the arrow keys as soon as they appear, and screen readers announce them as menu items like the rest.
Fixes#33374
Adding, updating or removing knowledge base files through the API sent back the metadata of every file in the knowledge base, and so did renaming a knowledge base or changing its access. These calls got slower as the knowledge base grew, so bulk ingestion through the API lost speed with every batch. Adding or updating files now returns only those files, while removing a file, renaming or changing access returns an empty files list. API clients that read the files list from these responses now get only the affected files; the full list stays available, paginated, from `GET /api/v1/knowledge/{id}/files`. Timings with a local mock embedding server that answers instantly, median of 5 runs (at 1,000 files the per-file work of a batch still hides the difference):
| Files already in the knowledge base | Call | Before | After | Response size before | Response size after |
|---|---|---|---|---|---|
| 1,000 | batch add of 100 files | 519 ms | 528 ms | 437 KB | 39 KB |
| 10,000 | batch add of 100 files | 679 ms | 476 ms | 4.0 MB | 39 KB |
| 10,000 | single file add | 184 ms | 36 ms | 4.0 MB | 0.6 KB |
Closes#31397
When a tool returned an image, for example Open Terminal reading a PNG, a native tool or an MCP screenshot tool, the image was sent to the model even when the model has Vision turned off. A provider serving a text-only model rejects that request, so the reply failed with an error like "At most 0 image(s) may be provided in one prompt", and every later message in the chat failed the same way. With Vision off the model now gets a short "[image]" note in place of each tool image, including images already saved in the chat, so stuck chats work again. The images stay saved, so they reach the model again once Vision is turned on.
Fixes#32720