📝 Changelog

v0.1.15

Features

Workspace

New workspace — Your Terminals, on an Infinite Canvas

Most terminal apps stack your sessions in a row of tabs. Workspace takes a different approach: it gives you an infinite canvas where you can place, resize, and arrange terminal cards freely — like a whiteboard for your command line.

When you're managing a deployment, tailing logs on three servers, and running a build locally, tabs force you to switch context constantly. Workspace lets you see everything at once. Lay out your terminals the way your workflow actually looks — side by side, clustered by project, or spread across a wide canvas you can pan and zoom through.

Terminal

• Drag and drop files from the system file explorer into the terminal to auto-input file paths

Settings & Account

• Added recovery key feature in Account Settings

• Support configuring a default editor for opening text/code files (#24; thanks MinJie Hong)

Platform & Build

• Added Windows ARM64 build support

Performance

• Chat messages now appear instantly after sending — no longer waits for database and network requests

Bug Fixes

Sync

• Fixed vault conflict timestamps showing as 1970 and sync toggle not syncing across devices

• Fixed multiple issues in the client sync mechanism

• Prevented empty data from overwriting cloud vault when secret key is not yet initialized

• Fixed race condition where cloud data was not synced on startup

Terminal

• Fixed ANSI black background not being transparent in acrylic mode (#23; thanks 扎西德勒)

Other

• Fixed Agent command execution on Linux not capturing output

Rumus v0.1.14

Bug Fixes

• Fix the issue where account-related information does not update automatically

• Optimize the error message displayed after entering an invitation code

Rumus v0.1.13

Features

Agent

• User messages now render with Markdown formatting (code blocks, links, lists, etc.), consistent with assistant messages

• Support for out-of-order approval of multiple pending commands — when the LLM returns multiple tool calls, users can approve them in any order via a pre-resolved approvals mechanism

• In Workspace mode, commands now execute in the target terminal's PTY instead of running in the background

Vault

• Duplicate host: quickly create a new host based on an existing host's full configuration (auth, proxy, jump chain, environment variables, etc.) via a copy button in the host edit dialog

• Global vault reset detection — when device sync detects a vault reset, the SecretKeySetup dialog now appears on any page with a toast notification, not just on the vault settings page

Auth & Account

• Non-subscribed users now see an "Upgrade" button in Account Settings, linking to the pricing page

• Added a "Top Up" button next to balance display in Account Settings

• MCP, Rules, and Skills features are now restricted to Pro subscribers

Bug Fixes

• Fixed out-of-order approval resetting tool call status to pending — onApprovalNeeded now checks for pre-resolved decisions before updating status

• Fixed Workspace multi-terminal target display and stop button race condition

• Simplified vault conflict dialog button styles — removed verbose description text, keeping only icons and labels

Rumus v0.1.12

Starting from this version, Rumus is fully usable without signing in or entering an activation code. Create terminals, connect to hosts, and use the AI agent right away — no account required. Sign in only when you need cloud features like sync and vault.

Users who participate in the beta and provide feedback will receive a complimentary Pro subscription and an exclusive Black & Gold theme, distributed on a rolling basis.

Features

UI & Experience

• Dramatically improved startup performance

• Vault settings page now shows a persistent description with a "Learn More" link at the top, with dynamic per-tab descriptions that update as you switch tabs

• Improved Rumus Dark theme readability — brightBlack color changed to a more legible blue-purple gray

• User profile data (user info, balance, subscription tier) is now cached

Auth & Account

• Invite codes: generate your personal invite code from Account Settings, share it with others, and redeem codes you receive. Each code is single-use

• Simplified subscription tiers — removed the Max tier and unified everything under Pro. Built-in model access and cloud search are now gated by Pro subscription

• Vault key conflict detection on login: when a local vault already exists and the logged-in account also has a cloud vault, the app detects encryption metadata differences and presents a conflict dialog with three options — use cloud vault, use local vault, or cancel login

• Removed the Onboarding wizard flow, login check logic simplified

• Add balance display to the account interface

i18n

• Added 4 new languages: Traditional Chinese, Japanese, Korean, and Spanish

• Language selector now displays all languages in their native names (e.g., 日本語, 한국어, Español)

• Improved product copy: better empty state descriptions, enhanced SSH security warnings, vault tab descriptions, and chat input hints

Bug Fixes

• Fixed Host Management dialog showing "Initialize Secret Key" instead of "Recover Secret Key" for users who already have a key

• Fixed sync toggle for non-Pro users — sync settings and vault sync switch are now auto-disabled, "Sync Now" button is disabled,

• Fixed model list API requiring authentication

Rumus v0.1.11

Features

AI / Agen

• Agent subtasks can now properly display approval buttons when executing commands, instead of hanging indefinitely

• Improved smart history completion: now reads more shell history entries and ranks suggestions using a heuristic scoring algorithm based on recency and frequency (thanks donny.rui)

• Smart completion now works in nested shell environments, such as executing commands inside Docker containers (thanks donny.rui)

• Interactive commands (sudo/ssh/passwd, etc.) are now auto-detected and forced into interactive mode to prevent output loss on timeout

UI & Experience

• Improved approval button interactions: buttons now share the same default appearance, with "Approve" turning primary color and "Reject" turning red on hover, plus active press feedback

• OpenAI-compatible providers now use the full endpoint URL provided by the user, fixing 404 errors for non-standard API paths like ZhiPu GLM

Auth & Account

• Logging out now fully resets sync state and settings timestamps, preventing old account configurations from polluting a new account's cloud data

Bug Fixes

• Fixed agent chat history disappearing after manually canceling — accumulated message content is now properly saved on abort

• Fixed agent tool calls running in parallel causing subtasks to deadlock; switched to sequential execution with a 5-minute timeout safeguard

• Fixed ongoing agent sessions being lost when navigating to the Settings page and back

• Fixed pending approval sessions losing data when switching chats — streaming is now automatically stopped before switching

• Fixed agent stop button not actually stopping generation and command execution

• Fixed closing a tab hanging when an agent session is active

• Fixed SSH remote terminal info falling back to local Windows system info when not connected

• Fixed command whitelist storing only the first word; now stores command + subcommand prefix (e.g., npm install)

• Fixed title generation not falling back to the first sentence or timestamp on failure

• Raised default command timeout from 5 to 10 minutes

• Fixed parallel subtask UI status not updating in real time until all tasks finished

• Fixed new users' "Initialize Secret Key" button being unresponsive in Host Management (thanks 纄蕺)

• Fixed copy/paste not working in Workspace split-pane sub-terminals, and smart completion failing after entering Docker containers (thanks donny.rui)

• Fixed OpenAI-compatible provider path concatenation error (e.g., /v4/v1/chat/completions) (#21; thanks 扎西德勒)

• Fixed agent being unable to read the current terminal's command history

Rumus v0.1.10

Features

AI / Agent

• The Agent's command execution has evolved from background processing to real-time terminal interaction. Commands are now dispatched directly to the user's terminal with automatic result retrieval, ensuring full visibility of the entire execution history. (thanks 嘻嘻嘻嘻嘻嘻)

- Added OpenAI-compatible provider with custom API endpoint support — you can now connect to any OpenAI-compatible service by configuring a custom base URL (thanks 扎西德嘞)

- Added DeepSeek, Kimi, and ZhiPu Coding model providers

• Added GLM-5 model and updated static model lists for all providers

• Support for remote MCP server connections (SSE + Streamable HTTP)

• Agent commands now support queued execution in the terminal

• Added "Integrate commands into current session" toggle — when disabled, the agent outputs commands as text instead of executing them interactively

UI & Experience

• Added theme color picker with 12 preset theme colors (#13; thanks donny.rui)

- Added terminal color scheme picker with 18 built-in color schemes (#20; thanks xiaosun)

- Added smart completion settings — smart completion can now be toggled on/off in settings

- Adjusted popup menu and dark mode menu background opacity

• Added global proxy settings with three modes: system proxy, custom proxy, and no proxy

Linux

• Re-exported icons from Figma with all required sizes, fixed blurry app menu icons

• Fixed an issue where Vim became unresponsive to any keypress during file editing (thanks donny.rui)

Mac

• Fixed an issue where Vim became unresponsive to any keypress during file editing (thanks hao he)

Bug Fixes

• Fixed new users seeing the key setup dialog without any guidance when first opening Host Management (#19; thanks Qingqin Lu)

• Fixed smart completion Tab key not completing and arrow keys causing the suggestion popup to disappear (thanks donny.rui)

• Fixed Git Bash failing to launch when its path contains spaces; Git Bash and CMD now default to shell integration disabled

• Fixed Anthropic API error where max_tokens must be greater than budget_tokens in thinking mode

• Fixed OpenAI reasoning and max_tokens parameter errors

• Fixed auto-approve toggle incorrectly approving non-whitelisted commands

• Fixed smart completion input mode not restoring correctly after command execution

Rumus v0.1.9

Bug Fixes

• Fixed an issue where the window did not follow the mouse while dragging

• Fixed the Esc key not responding after the terminal entered interactive mode

Rumus v0.1.8

Features

UI & Experience

• Both left and right sidebars are now resizable — drag the edge to adjust width

• Double-clicking the title bar now correctly toggles maximize/restore

• Simplified the onboarding flow by removing the secret key setup step

• Updated application icon

AI / Agent

• Removed the interactive command dispatch to terminal — the agent no longer sends sudo/ssh commands to the user's terminal for manual execution

Linux

• Automatic terminal renderer fallback to Canvas on X11

• Acrylic theme is now disabled on X11 with automatic fallback to Dark theme

• Added missing desktop icon sizes

Bug Fixes

• Host management dialog now correctly shows the secret key recovery flow instead of PIN unlock when the vault is not initialized

• Fixed an issue where secret key files could sometimes fail to load during key recovery

• Fixed title bar double-click not working

Rumus v0.1.7

Features

AI / Agent

• Interactive commands dispatched to the terminal now end the agent's tool loop, allowing users to complete the interaction before the agent continues. The agent prompts users to notify it once they're done.

UI & Experience

• Animated skeleton bubbles (bouncing dots) now appear while waiting for the AI's first token, replacing the previous "Generating..." text in the header

• Unified all dialog scrollbars for consistent styling across Keychain, Snippets, Accounts, Known Hosts, and Snippet List dialogs

• Optimized the host edit dialog layout — icon color picker merged inline, Shell Type moved from advanced settings to the basic info tab

• Improved the onboarding flow logic

Bug Fixes

• Fixed keyboard shortcuts not working in Vim mode

• Fixed an error when dragging non-terminal tabs to a new window

• Fixed an issue where backslashes were stripped from Windows paths, preventing terminals from launching

• Fixed host management reading the key file path instead of the file contents after selecting a private key file

• Fixed SSH sessions freezing during data‑intensive transfers.

Rumus v0.1.6

Bug Fixes

• Fixed an issue where the PATH environment variable failed to load correctly on macOS. (#18; thanks Robot)

• Optimized the display of the autocomplete menu.

• Fixed an issue where pressing Tab failed to trigger completion when the input exactly matched a suggestion.

Rumus v0.1.5

Features

AI / Agent

Plan Mode

Plan Mode enables the AI to break down complex tasks into structured, multi-step execution plans before taking action. Instead of immediately running commands, the agent first creates a plan outlining its approach — complete with ordered steps, reasoning, and a clear goal. The plan is presented to you for review and approval before any execution begins. As the agent works through each step, progress is tracked in real time with visual indicators (pending, in-progress, completed, failed).

Plan Mode is always available — the AI automatically decides when a task is complex enough to benefit from a plan. No manual toggle is needed.

Sub Agent

Sub Agent (also called Sub Task) allows the AI to delegate complex subtasks to independent child agents. When the primary agent encounters a problem that benefits from focused research, risk assessment, or parallel investigation, it spawns a sub agent that operates autonomously with its own context — while forwarding all tool calls and outputs back to the main conversation for full transparency.

Sub Agent is always available — the AI decides when task delegation is appropriate. No manual toggle is needed.

MCP (Model Context Protocol)

MCP is an open standard (originally introduced by Anthropic) that lets AI agents connect to external tools and data sources through a unified protocol. In Rumus, you can add MCP-compatible servers (e.g., filesystem tools, database connectors, API wrappers) and the agent will automatically discover and use their tools during conversations.

To configure MCP: go to Settings → AI → MCP, click Add, and paste a server configuration in JSON format. Each server has an enable/disable toggle. When enabled, the server connects automatically when the AI sidebar opens.

Skills

Skills are reusable instruction packs that extend the AI agent's knowledge and behavior. Each skill consists of a name, description, and detailed instructions. The agent sees all enabled skill names and descriptions, but only loads the full instruction content on demand — keeping token usage efficient while giving the agent access to specialized knowledge when needed.

To manage Skills: go to Settings → AI → Rules and Skills. Click Add to create a new skill, or upload a skill file. Each skill has an enable/disable toggle.

Cloud Web Search

Cloud Web Search uses the Rumus Search API to provide the agent with faster, more reliable web search results compared to the default local DuckDuckGo scraping. Search results include richer metadata such as extra snippets, content age, and site information.

To configure: go to Settings → AI → General and toggle Cloud Web Search. Enabled by default. When disabled, the agent falls back to local browser-based DuckDuckGo Lite search.

Other AI Improvements

• Parallel tool execution — multiple independent tool calls now run concurrently

• Automatic retry on HTTP 524 timeout errors

• Full tool_calls and tool_results context now persisted and restored when reopening sessions

• Conversation rename request delayed 500ms to avoid racing with the main generation request

• Tool targetName persisted to database for display continuity

• tool_call / tool_result message pairing guaranteed in streaming

Workspace

• Bidirectional workspace sync — remote changes now automatically apply to local state

• The monitoring card supports monitoring of the currently running computer

UI & Experience

• We have re-optimized the display effects of acrylic themes across various systems

  

• Now, under the acrylic theme, you can manually control the transparency of the background color (#17; thanks donny.rui)

  

• Acrylic theme color refinements and removal of redundant background overlays

• Sidebar now includes Files / Scripts tab switcher with a script list and file upload button

Linux

• Added manual download update prompt for deb/rpm installation users

• Optimized startup speed

• SwiftShader software renderer detection with automatic Canvas rendering fallback

• Removed Nvidia X11 WebKitGTK DMA-BUF environment variable workaround

• Removed Linux acrylic noise texture effect

• Clipboard fix for Linux

Bug Fixes

• Fixed tool execution status being lost across sessions

• Fixed Zod v4 tool parameter serialization issue

• Fixed user_info missing causing session restore failure

• Fixed deleted rules still being injected into system prompt

• Fixed Progress card status icon stuck on loading

• Fixed autocomplete menu not closing on Esc

• Fixed free-tier users hitting "Database not initialized" and "BadFileKey" errors on first PIN setup (#14; thanks WEP)

• Fixed bash terminal color rendering, web_search parameter compatibility, and log optimization

• Fixed Nvidia GPU auto-detection and WebKitGTK DMA-BUF workaround on Linux

Rumus v0.1.4

Features

AI / Agent

• Rebuilt the Agent core architecture from the ground up

• Added image support for Agent conversations, including paste-to-upload and zoom controls

• Introduced token-based context management using js-tiktoken, replacing the fixed message count approach

• Added Max Mode setting — when disabled, context is limited to 20k tokens; when enabled, uses the model's full context length

• Automatic LLM summarization when context usage reaches 80% threshold

• Added auto-naming toggle for conversations — choose between AI-generated titles or using the first message

• Hide inline completions when the terminal enters interactive mode

• Introduced multi-terminal support with per-tab isolated chat sessions

• Each tab's agent now retrieves its own terminal context instead of sharing global state

• Agent tools support a target parameter to execute commands in a specific terminal

• Sidebar history automatically filters by the current tab's profile, host, or workspace

• Detached mode: viewing history from a different context disables command execution

Workspace

• Added executeInTerminals / executeInAllTerminals for batch execution across multiple terminals

• Workspace-aware AI agent context retrieval and command execution

• Added onboarding prompt when creating the second card in a workspace

Auth & Account

• Added a note on the login onboarding step explaining that sign-in is required during beta

UI & Experience

• Refined the chat input: removed Markdown preview, moved zoom buttons to the top-right corner, added slide transition animation, replaced the paper-plane send icon with an arrow

• Added a ligature hint in terminal font settings to inform users about automatic ligature rendering

• Added a first-run onboarding flow

• Improved community link entry points

Linux

• Improved overall display and styling on Linux

Bug Fixes

• Fixed frequent auth session expiration

• Fixed access token not being refreshed on a timer

• Fixed errors during auto-naming and summary generation with built-in models

• Fixed cross-device sync resetting Max Mode and auto-approve tool settings

• Fixed CWD tracking using a stale static value (#11; thanks Wang zixu)

• Fixed default model ID format not matching built-in model ID format

• Fixed selected model being reset after refreshing the model list

• Fixed terminal tab session never being created, preventing message sending

• Fixed newly created sessions missing terminal context and session info callbacks

• Fixed error when opening chat history with no session created

• Fixed browser engine download dialog appearing when there is no active session

• Enabled opening historical conversations directly from the Chat History page without switching to a terminal tab

• Fixed Agent thinking process not being displayed

• Fixed garbled Chinese input on macOS in production (#6; thanks Wang zixu)

• Fixed missing syntax highlighting for command output on Linux

• Changed all path comparisons to case-insensitive to fix replacement issues on case-mismatched paths (#8; thanks Wang zixu)

• Fixed detected bash shell being discarded during initialization