Open Customize → General for appearance, language, notification, sound, account, and update preferences. Reasoning visibility is controlled within each conversation turn.
Appearance and language
Choose the available appearance mode and interface language. The language setting affects interface text; you can separately ask the agent to write in a particular language.
Write the report in English and retain the original-language titles in
the bibliography. Explain translated technical terms when ambiguous.
Notifications
General offers notification preferences for agent completion, permission requests, and errors. Enable the signals you want to receive and allow notifications at the browser or operating-system level when prompted.
A notification setting controls alerts; it does not schedule a future run or keep work running while the application is closed.
Sounds
Enable or disable sounds, adjust volume, and choose the available sound for completion, permission requests, and errors. Use quiet settings when you prefer to monitor progress in the workspace.
Context and account
Context compaction is automatic; there is no percentage selector in General. See Context and handoffs for capacity, manual compaction, and preserving important work as a conversation grows.
Check the account and funding workspace before paid work. Ace explains account connection, Wallet access, and switching workspaces.
Usage and privacy
Open Customize → Usage for date-filtered activity and CSV exports. Managed Wallet charges and device-local provider activity have different scopes; see Usage reports.
Under General → Data & privacy, review Share session traces and delivery status. Local models and personal keys do not disable trace sharing automatically. See Privacy and data.
Reasoning visibility
Use Show reasoning and activity / Hide reasoning and activity above a turn to expand or collapse its steps. Each turn remembers its own choice; changing one does not move or hide the history in other turns. New live turns open automatically and stay open when they finish; a turn you explicitly collapse stays collapsed. Answers, scientific results, pending approvals/questions, and failed tool calls remain visible when steps are collapsed.
There is no separate global reasoning toggle or Detailed/Compact mode. Readable provider text is shown inline, with routine action headings omitted. Providers may supply summaries or no readable reasoning; OpenScience cannot reveal private reasoning the provider did not send.
Consecutive reasoning fragments appear in one expandable row. Completed reads, searches, and edits stay grouped while a long task runs; expand a group to inspect each original tool result. Failures and pending requests remain separate. Patch summaries count the files reported by the tool.
Updates and release notes
Use the update controls available for your installed interface. The desktop app and CLI have different update entrypoints; see Installation and updates.
General also includes the preference for showing release notes. Read the notes when a guide differs from the installed version, especially for model access or tool availability changes.
Find other settings
| Need | Guide |
|---|---|
| Model or personal-provider access | Models. |
| Local endpoint connection | Local models. |
| Tool and service setup | Explore tools. |
| Reusable procedures | Skills. |
| Action approval | Permissions. |
| Data location and recovery | Files and storage. |
| Repeatable project settings | Configuration. |