The interface release, and two of its five features are about finding things you have already done.
Chat search. A box under New Chat, Ctrl+K. Typing filters the list by title as you type. Enter
searches message text and shows matching chats with highlighted snippets. Words can appear in any
order and in different messages; "quotes" keep a phrase together. Only your messages and the
assistant's text are searched, not tool output. Jump to message is the half that makes it useful:
opening a result shows the matching messages with your words marked, in the desktop app, the web UI
(and for a chat already open), and the CLI (/load <#> <msg#> prints the match). Six months of
conversations with an agent is a lot of text, and "which chat was that in" was answerable only by
scrolling.
Titles by the model. Edit Chat replaces the sidebar's Save button with one dialog: rename,
Generate a title from the chat's user and assistant text, or export as Markdown. Bulk Rename
Chats in Settings does it to every chat, behind a warning, with a progress bar and Stop between
chats. Each chat records where its title came from (title_source: generated, typed, automatic), so a
bulk run only touches the automatic ones and never overwrites something you named.
Two security fixes in the web UI, both about a model reply being treated as trusted content.
Raw HTML in a reply was passed straight through by Python-Markdown, so <img onerror=…> or <script>
executed in the page, and a prompt-injected page fetched with fetch_url could supply it. HTML in
a reply is now shown as text. Separately, a javascript: or data: link in a reply survived into the
page: links and images keep only http, https and (for images) data:image/*. The attack chain is
worth spelling out, because it is the chain every agent product has: model output echoes a fetched
page, that page shares an origin with an API that can enable YOLO and send messages, and a link in the
reply is a click in your session.