v0.9.8

Added

• 🏠 Choose how .cptr is handled in projects. Admins can now turn the automatic .gitignore entry on or off, so local chats, memory, caches, audio samples, and generated files stay private by default unless you choose otherwise.
• 🤖 A llama.cpp connection mode. OpenAI-compatible connections can now be marked as llama.cpp, so Qwen and other local reasoning models can receive prior thinking in the format llama.cpp expects.
• 🧩 Skills can open their own companion files. view_skill can now load files such as references/guide.md from the selected skill folder, without opening broader home-directory access.
• 🌐 Sized browser screenshots. Browser tasks can request a screenshot at a specific size and Computer will restore the normal page view afterward.

Changed

• ⚙️ Admin switches behave like switches. In Models, Agents, Connections, Messaging, and Tool Servers, click the row text to edit and click the switch only to turn something on or off.
• 🔎 Workspace search respects .gitignore. File search and content search now skip ignored folders and files, keeping generated output, caches, and local Computer data out of normal results.
• 🧠 Reasoning replay is stricter by default. Computer now keeps strict OpenAI-compatible connections clean, and only sends llama.cpp-style reasoning_content when the connection is set to llama.cpp.

Fixed

• 🧠 The chat size meter no longer freezes behind llama.cpp. Computer now normalizes token usage from OpenAI-compatible streams and sends live context updates to the chat while a response is still running.
• 💬 Compacted chats survive regenerated answers better. Summaries are saved on a stable kept user message when possible, so regenerating an assistant answer is less likely to lose the compacted history.
• ✂️ Manual compact keeps the latest turn available. Compacting a chat now summarizes the older branch and leaves the newest message ready for the next response.
• 🧠 Prior reasoning is preserved more reliably. Reasoning from ordinary replies, tool-call turns, Chat Completions streams, and Responses streams is less likely to be dropped before the next model request.
• 🎨 Token usage details match the chosen theme. The usage popover now uses Computer's app surface colors instead of the wrong gray background.
• ✨ Messages render more faithfully. Your own messages can show Markdown, and raw markup appears as text instead of disappearing.
• 🗂️ Commit suggestions are less brittle. If the model returns a plain commit message instead of perfect structured output, Computer can still use the useful parts.
• 📝 File edits keep text encoding consistent. Created and edited files are written as UTF-8, which avoids surprises with non-ASCII project files.

v0.9.7

Fixed

• 💬 Chat controls match your appearance. The lower edge of chats now blends in with the look you chose for Computer.

v0.9.6

Added

• ⏰ Follow-up timers for chats. Computer can now return to a chat at the right time to continue work, check again, or follow up.

Changed

• ✨ Clearer change reviews. Changes in files are easier to spot, including larger edits.

v0.9.5

Added

• 👀 Never lose track of a finished chat. Unread markers now appear in tabs and chat lists, with a count beside each workspace.
• 🌐 Browser tasks in Docker. A browser-ready Docker option is now available when your chats need to use the web.

v0.9.4

Fixed

• ⚡ Your model choices are ready sooner. Computer now gets them ready as it opens and keeps the last working list if a check fails.
• 👋 More dependable restarts. Computer now finishes its open work more reliably before it closes.

v0.9.3

Changed

• 🎨 Your appearance choice follows you. Sign-in and setup now use the same look you picked for Computer.

Fixed

• 🤖 Pi only appears when it is really there. A different program with a similar name will no longer show up as Pi.

v0.9.2

Added

• 💬 Helpful planning questions. When a plan needs your input, Computer can now ask a few focused questions with clear choices and a recommended answer.

Changed

• 🧠 Each chat remembers its own choices. Your selected model and chat options now stay with that conversation instead of carrying over from another one.
• 🏠 A more capable Home. Open files from conversations while using Home, and keep those file tabs available as you move between tabs.
• 🎨 A more consistent look. Your appearance choice now carries through to browsers, terminals, editors, previews, menus, and other everyday parts of the app.

v0.9.1

Fixed

• 🏠 Home chats work like workspace chats. Home keeps chats, terminals, and browser pages alive while you switch tabs, streams replies as they arrive, and correctly loads global skills.

v0.9.0

Added

• 🌐 A browser in your workspace. Open websites and local app previews in their own tabs, with back and forward navigation, mobile views, and display-quality choices.
• 🤖 More coding agents. Add Gemini or Pi alongside the coding tools you already use.
• 🔎 Search inside files. Find file names and matching text, then jump straight to the right line.
• 💬 A more useful home screen. Start a chat, terminal, or browser before opening a workspace, and arrange them side by side.

Changed

• 🗂️ Easier chat organization. Rename chats, copy their saved location, and load more of a workspace's chats without leaving the sidebar.
• ✨ More control over the view. Choose a wider layout and decide whether tool details stay expanded.

v0.8.8

Added

• ✨ More flexible layouts. Split any view again and again, resize each section, and drag tabs exactly where you want them.
• 🤖 Commit-writing help. Get a suggested commit title and description from your staged work.
• 📁 Create folders as you browse. Make a new folder without leaving the workspace picker.
• 💬 An easy way to share feedback. Send feature ideas from the sidebar.

Fixed

• 👀 Updates stay dismissed. Closing the update notes no longer brings them back after a quick refresh.