- Updated theme count from 12 to 18 in description
- Added 4 missing light themes: Solarized, One Light, Gruvbox Light, Catppuccin Latte
- Fixed "GitHub Light" to "GitHub" to match actual theme name
- Fixed Settings path from "Appearance → Theme" to "Themes tab"
- Added Custom Theme section documenting the theme builder
- Fix "Global Access" → "Live Sessions" (only live sessions accessible)
- Rename "Static Port Configuration" → "Custom Port Configuration" to match UI
- Correct port range from 1024-65535 to 1-65535
- Fix "Use Custom Port" → "Custom Port" toggle label
- Add UUID clarification for security token
- Expand Mobile Web Interface with Core Features, Gestures, Input subsections
- Add Connection Handling section (auto-reconnect, offline mode, status)
- Add notes, tips, and related links section
- Use em-dashes for consistency with other documentation
Changes:
- Fixed Claude Code model selection: was incorrectly documented as supported
via --model flag, but source shows supportsModelSelection: false (configured
via Anthropic account)
- Changed "OpenAI Codex" to "Codex (OpenAI)" throughout for consistency
- Fixed Codex slash commands: changed from ⚠️ to ❌ since they don't work in
exec mode which Maestro uses
- Updated Codex slash commands link to official OpenAI docs
- Fixed OpenCode slash commands: changed from "Not investigated" to "Not
supported" per source code
- Enhanced OpenCode note to mention OPENCODE_CONFIG_CONTENT env var for YOLO
- Added "Context operations" row for all providers (merge/export/transfer)
- Added "Thinking display" row for all providers documenting streaming output
- Updated description frontmatter for consistent naming
- Added "OpenSpec CLI Commands" section with table of essential commands
(list, list --specs, show, validate, archive, spec list --long)
- Fixed Stage 1 workflow to document full process including project.md
review and openspec list commands
- Fixed validation command format to include required change-id parameter
- Added --yes and --skip-specs flags documentation for archive command
- Expanded /openspec.implement description with phase grouping details
- Updated "Viewing & Managing Commands" section to accurately describe UI
- Fixed Spec-Kit directory location from "Project root" to "specs/"
- Changed tips to use "verb-led IDs" terminology per AGENTS.md conventions
- Standardized to em-dashes for consistency with other docs
- Added mention that MCP server is hosted by Mintlify
- Added proactive search behavior explanation
- Added Cursor and VS Code configuration instructions
- Clarified transport type as HTTP/HTTPS (Streamable HTTP)
- Added note about page indexing limitations
- Verified all existing information is accurate
Major fixes:
- Toggle Sidebar was Cmd+B, actual shortcut is Opt+Cmd+Left (renamed to Toggle Left Panel)
- Toggle Right Panel was Cmd+\, actual shortcut is Opt+Cmd+Right
- Document Graph Tab cycling didn't exist in code, removed it
- Document Graph Enter key behavior was wrong: re-centers for docs, opens URL for external
- Keyboard Mastery levels were completely wrong (Novice/Apprentice/etc vs Beginner/Student/etc)
- Keyboard Mastery location was "status bar" but it's actually in Shortcuts Help panel
Added missing shortcuts:
- New Agent Wizard, New Group Chat, Navigate Back/Forward
- Toggle Input/Output Focus, Focus Left Panel, System Log Viewer, Process Monitor
- Toggle Bookmark, Maestro Symphony, Toggle Auto Run Expanded, View Git Diff
- Toggle Tab Star, Toggle Tab Unread, Filter Unread Tabs, Open Prompt Composer
- Go to Tab 1-9 and Go to Last Tab
- File Preview Go Back/Forward
- Context-sensitive filter shortcuts (Cmd+F in different contexts)
- Added performance best-practices guide for React and main process tuning 📘
- Introduced `buildFileTreeIndices` for fast, reusable markdown file lookups ⚡
- Updated `remarkFileLinks` to accept prebuilt indices with backward compatibility 🧩
- Memoized file-tree indices in AutoRun, FilePreview, and MarkdownRenderer for speed 🚀
- Expanded test suite to cover indices building and indexed link resolution 🧪
- Made temp-file cleanup asynchronous to keep the main thread snappy 🧹
- Cached shell path resolution to avoid repeated synchronous filesystem checks 🗄️
- Precompiled leading-emoji regex to speed up session name sorting 🔤
- Consolidated SessionList filtering/grouping/sorting into one efficient memo pass 🧠
- Memoized TabBar tabs, computed labels, and style objects to cut rerenders 🎛️
- NewInstanceModal now preserves SSH config during agent re-detection flows 🧭
- Tests now mock remote `fs.stat` to validate SSH working directory reliably 🧪
- NewInstanceModal tests wait for debounced remote path validation before creating ⏱️
- Leaderboard “Submit” button stays hidden after success to avoid resubmits 🚫
- Leaderboard “Sync from cloud” is now available even after successful submit 🔄
- Leaderboard “Opt Out” action remains accessible after a successful registration 🧾
- Autorun synopsis prompt bans session-context preambles for cleaner summaries ✍️
- SSH remote selection now works even before choosing an agent 🚀
- NewInstanceModal now reads pending SSH config for enablement/host display 🔧
- Agent detection reliably re-runs when switching between remote and local 🔁
- Wizard recovery test now programmatically toggles SSH to bypass JSDOM quirks 🧪
- Wizard tests use real timers to validate React effects correctly ⏱️
- NewInstanceModal tests verify detect() called with selected SSH remote ID 📡
- Agent selection test flow now waits for aria-selected state properly ✅
- Tests stop relying on remote path validation and fragile placeholder behavior 🧹
- SSH selector tests consistently target the combobox select element 🎛️
- Leaderboard stats layout upgraded from grid to flexible proportions 🏆
- Detect agents on SSH remotes via IPC `agents:detect(sshRemoteId)` 🌐
- Show friendly “Unable to Connect” UI when remote agent detection fails ⚠️
- Re-detect agents instantly when switching SSH remote selection in modals 🔁
- Wizard now persists SSH remote choice across step navigation 🧭
- Remote directory validation now checks existence via `fs.readDir` first 📁
- Git repo checks and Auto Run docs lookup now support SSH remote IDs 🛰️
- Directory screen hides Browse button for remote sessions, adds remote hints 📝
- Agent selection UI revamped: name + location dropdown, clearer header 🧩
- Add `showThinking` option to tabs and merged sessions, default false 🧠
- Export `AGENT_DEFINITIONS` for reuse in remote detection logic 📦
- Compaction now triggers earlier: 2k tokens or 8 exchanges 🎯
- Added extra compaction fallbacks when context gauge resets unexpectedly 🔁
- Read-only tabs now force “return plan in Markdown” instructions 🧾
- Auto Run without worktree automatically runs in read-only/plan mode 🛡️
- ThinkingStatusPill now accepts prefiltered thinkingSessions for speed ⚡
- InputArea precomputes thinking sessions and memoizes command filtering 🚀
- MainPanel memoizes active tab lookup to cut per-keystroke work 🧠
- TerminalOutput memoizes active logs and reduces scroll update frequency 🖥️
- Batched session updates track context high-water mark with explicit reset 🌊
- Wizard adds one-click debug log download right in the conversation UI 🧰
- Leaderboard registration now submits cumulative stats safely for multi-device sync 🏆
- AutoRun prompt now requires a concrete “what I did” synopsis first 🧭
The wizard was using agent.command ("claude") instead of agent.path
("/opt/homebrew/bin/claude") when spawning processes. In packaged
Electron apps, PATH may not include agent locations, causing ENOENT
errors when no existing agents had been created.
Fixes#171
The /wizard command now respects the user's configured Auto Run folder
path instead of always creating "Auto Run Docs" at the repository root.
Fixes#169
- Document labels now hide “.md” extension for cleaner progress display ✨
- Full filename (with “.md”) moved into hover tooltip for quick clarity 🧾
- Document name text now truncates gracefully to prevent layout overflow 🧩
- Improved flex sizing so progress bar stays visible in tight spaces 📊
- Add initialRect to prevent flushSync warning during initial render
- Add scroll-to-selected effect for keyboard navigation (arrow keys)
- Use measureElement ref for dynamic row sizing instead of manual refs
- Adjust estimated row heights to better match actual content
- Remove unused itemRefs
The logsEndRef div was conditionally rendered only when session.state
!== 'busy', which prevented Cmd+Shift+J (scroll to end) from working
while the agent was actively processing. Now always rendered.
- Fresh app icons for macOS and Windows builds, looking sharper than ever 🖼️
- New opt-in global Leaderboard tracking via <a href="https://runmaestro.ai">RunMaestro.ai</a> 🚀
- Themes documentation revamped into Dark, Light, and Vibe categories 🎨
- Theme lineup refreshed with Catppuccin Mocha, Gruvbox Dark, and Ayu Light 🌈
- Brand-new Vibe themes added: Maestro’s Choice, Dre Synth, InQuest ✨
- New docs screenshots added to better showcase Maestro’s experience 📸
- Sessions now support bookmark toggling via Cmd+Shift+B and UI actions 🔖
- Added global Leaderboard showcasing Auto Run records and community rankings 🏆
- Leaderboard includes conductor badge, social links, and detailed stat sync 🌐
- Documented Tab Switcher fuzzy search with quick numbered tab jumps 🔎
- Tab Switcher now shows token count, cost, and context usage insights 📊
- Added screenshot-rich Shortcuts Settings guidance for remapping keys 🛠️
- Enhanced Shortcuts Help modal docs with search and mastery checkmarks ✅
- Introduced new default shortcut: Toggle Bookmark (Cmd+Shift+B) 🔖
- Wired Toggle Bookmark into main keyboard handler for active sessions ⚡
- Refreshed documentation screenshots, including new shortcuts modal image 🖼️
- Generate playbooks mid-session with the new Inline Wizard flow 🧙
- Add confidence gauge and organized wizard subfolders for generated docs 📈
- Launch **Maestro Symphony** to donate tokens and ship OSS PRs 🎵
- Browse/filter/search Symphony projects and issues directly in-app 🔎
- Auto-clone repos, run Auto Run docs, and open draft PRs automatically 🚀
- Track Symphony contributions with active/history/stats dashboards 📊
- Make leaderboard submissions multi-device safe using delta-based aggregation 🔁
- Stop image flicker with synchronous cache-backed Markdown image loading 🖼️
- Debounce Auto Run preview scroll persistence to cut noisy re-renders ⏱️
- Rename/delete in File Explorer updates tree instantly—no full refresh ⚡
- Gist publish modal now shows previously published URL and details 📌
- Copy gist URL in-app with instant “Copied!” feedback button 🧷
- Open published gists directly in your browser from the modal 🌐
- Re-publish flow added, with back navigation and replacement warning 🔁
- File preview now highlights the Gist icon when a gist exists 🎯
- Published gists are remembered per file path and restored on startup 💾
- Gist metadata now tracked (visibility and publish timestamp) for each file ⏱️
- App persists gist mappings to settings automatically after publishing 🗄️
- Community Discord links updated everywhere to <a href="https://runmaestro.ai/discord">runmaestro.ai/discord</a> 🔗
- Test suite expanded to cover existing-gist UI, copying, and republish flows 🧪
- Added Lightbox image deletion with confirmation modal and keyboard shortcut 🗑️
- Expanded Lightbox test coverage to fully validate delete flows end-to-end 🧪
- Generate and persist a unique installation GUID on first run 🔑
- Tag Sentry crash reports with installationId for better correlation 🧷
- Exposed `leaderboard:getInstallationId` IPC + preload API for renderer access 🔌
- Leaderboard submissions now auto-include installId (server-mapped field) 📤
- Send clientTotalTimeMs to help detect multi-device time discrepancies ⏱️
- Added Quick Action to copy Install GUID to clipboard for debugging 📋
- Tuned HistoryPanel virtualization row height estimates for smoother scrolling 📜
- Fixed React hook dependency for staged image removal callback stability 🪝
Increased UpdateCheckModal width from 500px to 625px to give release
notes more room to display properly.
Claude ID: 56e528a6-9479-464e-bdfa-6eef08f10ded
Maestro ID: b9bc0d08-5be2-4fdf-93cd-5618a8d53b35
Adds defaultEnvVars support to AgentConfig interface and sets
OPENCODE_CONFIG_CONTENT with permission allow-all for OpenCode.
This prevents startup hangs caused by external_directory permission
prompts in batch mode.
Closes#158
- OpenCode CLI now uses `run` batch subcommand with positional prompts 🚀
- Dropped `-p` prompt flag for OpenCode JSON mode compatibility 🧩
- Added `noPromptSeparator` for OpenCode positional prompt handling 🧠
- Implemented “Close All Tabs” action for faster session cleanup 🧹
- Implemented “Close Other Tabs” to focus instantly on one tab 🎯
- Implemented “Close Tabs to Left” for browser-style tab management ⬅️
- Implemented “Close Tabs to Right” to prune clutter in one click ➡️
- Wired bulk tab-close handlers through App, Modals, MainPanel, TabBar 🔌
- Enhanced tab context menu with bulk close options and smart disabling 📋
- Updated tests to reflect OpenCode batch mode and UI copy tooltip 🧪
- Wizard now auto-continues when AI implies “let me research…” dead-ends 🧠
- Added robust deferred-response phrase detection to keep conversations flowing 🔍
- Introduced “Your turn” indicator when assistant awaits user input 💡
- Updated wizard system prompt to forbid deferred/async promises outright 🚫
- Prevented auto-continue infinite loops with a per-exchange trigger guard 🛡️
- Improved auto-continue UX with delayed send after UI updates ⏱️
- Added full test suite for deferred-response detection patterns ✅
- Strengthened NewInstanceModal tests with remote directory stat validation 📁
- NewInstanceModal tests now wait for debounced remote path validation ⏳
- Expanded icon mocking to include Loader2 for more complete test coverage 🎭
- SSH directory stats now include remote file and folder counts ⚡
- New incremental remote scanning finds changed files without full walks 🚀
- Baseline remote file listing added for faster subsequent refreshes 🧭
- File tree loading now streams live progress for slow SSH sessions 🛰️
- Fresh loading UI shows spinner, counters, and active scanned folder ⏳
- Sessions track file-tree loading state, progress, and last scan time 🧾
- New instance creation validates remote project path before enabling submit 🛡️
- Edit agent modal now verifies remote directory exists before saving 🔍
- Mind map nodes now label using filename (without .md) for clarity 🏷️
- Highlighted graph connections are now bolder for better visibility 🎯
- Add "Agent Native Commands" section to slash-commands.md explaining
which Claude Code commands work in Maestro's batch/print mode
- Document supported commands: /compact, /context, /cost, /init,
/pr-comments, /release-notes, /review, /security-review
- Document unsupported interactive commands: /mcp, /help, /clear,
/config, /model, /permissions, /memory, /rewind, /vim, /doctor, etc.
- Update provider-nuances.md to link to the new section
- Add tip for using CLI directly for interactive commands
Closes#146
- Windows terminal sessions now inherit full environment for reliable user tools 🪟
- Unix terminal launches keep minimal env while preserving essential PATH setup 🐚
- Command execution on Windows now preserves parent env with TERM override 🧰
- Remote BSD `stat` parsing fixed using ANSI-C quoting for newline output 📡
- Activity heatmap tooltip now anchors to hovered cell, not cursor location 🎯
- Tooltip positioning improved: centered below cell with smarter edge handling 🧭
- Removed mousemove-driven tooltip tracking for smoother heatmap interactions 🧊
- Auto-run image handling test updated for explicit `readFile` options argument 🧪
