Added data backup and restore for chats

The settings gain a data backup panel. It writes the chats of the chosen
workspaces, and optionally the temporary chats, into a single archive file
with the extension .aistudio-chats, and it imports such archives again.
The archive mirrors the chat storage, so restoring needs no conversion.

Documents the user attached are never copied into the archive. The chats
keep the absolute path of each document, which keeps them usable wherever
the documents live and avoids a second copy. Files AI Studio created itself,
such as transcripts, exist nowhere else; when the selection holds any, the
user decides whether they travel with the archive.

On import, chats which already exist, in any workspace, are either kept or
imported as additional chats with a new ID. Workspaces are merged by their
identity. An imported chat gets its own copy of every transcript the archive
did not carry, as a copied chat does, so deleting it never removes the
transcripts of the chat it came from.

An existing archive is only replaced once the new one is complete. Chats
which could not be read are reported instead of missing silently. Both
directions can be stopped at any time and report what was written.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
j-erlerandClaude Opus 5.5 committed 2026-09-26 16:25:39 +02:00
1 parent 4baf21656a
commit a8e8edc028
27 files changed
+2342 -3

No files matched your search

@@ -40,6 +40,9 @@
- Added an optional API key to every server you host yourself, among them LM Studio, llama.cpp, and whisper.cpp. Such a server may ask for one itself or sit behind a login your organization placed in front of it. So far, only Ollama and vLLM could be given a key.
- Added a setting for the audio quality used when your speech and your audio and video files are transcribed. AI Studio prepares every recording before it goes to your transcription provider, and you now decide how much detail it keeps: a lower quality travels faster, a higher one gives the transcription model more to work with. You find it in the app settings, right below your transcription provider. Thanks, Dominic Neuburg (`donework`), for this contribution.
- Added organization-wide management for the audio quality used when transcribing. IT departments can set the quality their organization works with and lock it, or leave it as a default their colleagues are free to change.
- Added data backup and restore for your chats to the settings. You write the chats of the workspaces you choose into a single archive file, which you can keep as a backup or take to another computer, and you import that file again whenever you need your chats back.
- Added chat backups that leave your attached documents where they are. When you back up chats in the settings, documents such as PDF or Word files are not copied into the archive. Your chats keep the place where each document is stored, so the documents stay usable wherever that place can be reached.
- Added transcripts to your chat backups when you want them. When you back up chats in the settings which hold transcripts of audio or video files, AI Studio asks whether the transcripts go into the archive, because they exist nowhere else.
- Improved loading web content in the assistants: it now uses the same reader as the Read Web Page tool, which extracts the main content of a page more reliably and skips navigation and boilerplate. Pages from your own network, including local servers, keep working as before. When a page cannot be read, AI Studio now says why instead of leaving the field empty.
- Improved the app icon. The previous one was generated by an image model; the new one was created based on it and keeps the familiar green landscape with the chat bubble. Because it is now a vector drawing, it stays sharp everywhere it appears: in your taskbar or dock, in the window list, and on the start screen while AI Studio is loading.
- Improved how AI Studio works out what a model can do. Every model family now stands on its own, together with the page it was read from, and our build refuses rules which contradict each other or name no source. That way, mistakes are caught before they ever reach you.