Changelog

BoltAI v2.5.0

• New: Usage metrics & estimated cost. Messages now store usage details, with chat-level totals for quick tracking.
• New: Workflow ordering & usage stats. Sort workflows, track usage count, and see recent activity.
• New: Thinking controls for Anthropic, Google, and OpenRouter. Configure effort/level and budgets across account, folder, agent, and chat.
• New: Codex CLI improvements. GPT-5.2 Codex models added and verification is more flexible with clearer warnings.
• New: Workflow/agent/prompt duplication. Quickly duplicate items and start a New Chat (Copy Configuration) from the sidebar.
• New: Advanced message editor. Expanded editing tools for message content and structure.
• Improved: Attachments. Higher file size limit for licensed users with clearer limits and errors.
• Fixed: Custom base URL model fetch. Model list requests now honor custom base URLs during provider setup.
• Fixed: Context policy updates. Switching profiles now keeps context policy changes consistent.
• Fixed: Markdown list indentation. Lists render with correct spacing and nesting.
• Fixed: Web renderer stability. Prevented a crash when extracting message text for rendering.

BoltAI v2.4.2

• New: Built-in Apple TTS support. Added Apple’s built-in text-to-speech voices to Voice settings.
• Fixed: Audio player window routing. Fixed the audio player opening in the wrong window.
• Fixed: Tools toggle stability. Prevented tools from auto-reverting or auto-enabling provider search when no tools are selected.
• Fixed: Agent tool list persistence. Fixed agent tool selections not saving reliably.
• Fixed: Gemini title generation. Fixed chats not auto-generating titles when using Gemini.
• Fixed: Think blocks in copy. Copying messages no longer includes <think> blocks.

BoltAI 2.4.1

• New: More built-in models. Added new models for Codex CLI, Claude Code, and Gemini CLI (GPT-5.2, Opus 4.5, Haiku 4.5, Gemini Pro 3.0).
• New: Extra High reasoning effort. Added support for xhigh reasoning effort.
• Fixed: Keyboard shortcuts being stolen. Fixed an issue where BoltAI could overwrite ⌘R and other system/app shortcuts.
• Fixed: Agent tools not applied in workflows. Fixed an issue where tools were not applied when using an AI Workflow + AI Agent with tools.
• Fixed: LLM parameters not saved. Fixed an issue where some LLM parameters might not be persisted.
• Fixed: ShotSolve screenshot state. Fixed an issue where ShotSolve could keep previous screenshots instead of clearing them.
• Fixed: Import hanging on macOS 26. Fixed an issue where import could hang on macOS 26.
• Fixed: Codex CLI auth refresh tokens. Sync refresh tokens back to the Codex CLI auth.json.
• Improved: Streaming proxy errors. Improved AI inference error handling in the streaming proxy.

BoltAI 2.4.0

• New: Apple Foundation Models (macOS 26+). Go to Settings > AI Services and click the plus (+) button to set it up. Tip: you can configure an AI Workflow to use Apple Foundation Models for free, 100% offline writing assistance. Note: tools are currently not supported for Apple Foundation Models.
• New: Advanced keyboard shortcuts. Go to Settings > Shortcuts to customize (e.g., new chat window, new temporary chat window, activate BoltAI chat, focus composer, regenerate response, copy last AI response, copy last AI response & close, edit last user message).
• New: Instant Workflow. Freely type your prompt in the Workflow Palette and trigger it immediately instead of using a pre-defined workflow.
• New: Reset Chat Context. Reset the current chat context marker with ⌘⇧K (configurable).
• Improved: Workflow hotkey trigger (no preview). Improved direct hotkey trigger for an AI Workflow (no preview), with a quick indicator in the case of “No Preview”.
• Improved: Japanese / Chinese IME. Better support for Japanese and Chinese input methods.
• Improved: Audio Player UI. The audio player now adopts the new Liquid Glass design.
• Fixed: Memory retention. Attempted to fix a memory issue where the app might retain large memory after idling for a long time.

BoltAI 2.3.1

• New: Liquid Glass support. BoltAI v2 now works on macOS Tahoe with Liquid Glass.
• Fix: Tools popover toggles. Resolved cases where some users couldn’t enable tools.
• Improved: RTL support. Better rendering and layout for right-to-left languages.
• Fix: List rendering. List items now render correctly in chats.
• Fix: Prompt imports. Addressed failures importing prompts from v1.
• Improved: Launch at Login & dock hiding. On login, the app hides its window and dock icon as expected.
• Fix: Window persistence. Window size and position are saved reliably.
• Improved: AI Workflow robustness. More reliable when triggered via direct keyboard shortcut.
• Improved: MCP handling. Better stability and control over MCP servers.
• New: MCP runtime ENV & PATH customization. Configure whitelists/blacklists and add PATH entries for tools like npx or uv.

BoltAI 2.3.0

• New: Kagi Search plugin. Premium web search with configurable results and Safe Search; bring your API key.
• New: WolframAlpha plugin. Query WolframAlpha for computational and factual answers.
• New: Default agent for root chats. Pick a default agent for new chats created outside folders; folder chats continue to use their own settings.
• Improved: Workflow Palette fuzzy search. Find workflows faster with fuzzy matching across names and descriptions.
• Fix: Workflow Palette listing. Prevented the palette from collapsing to a single entry.
• Fix: Tools popover race. Reduced state races when toggling tools to keep selections in sync.
• Fix: Window size/position. App now remembers window dimensions and location reliably.
• Fix: Workflow template editor. Addressed blank template edge cases when editing workflows.
• Fix: Agent & workflow saves. Resolved cases where edits to agents or workflows would not persist.

BoltAI 2.2.2

Workflow preview parity. Preview now respects your agent settings—provider, model, system instruction, temperature, token limits, penalties, context policy, and tool selection—so the inline preview matches the final send. Smarter selection capture. Hotkeys and the palette use a new PID-targeted copy helper that activates the frontmost app, restores your clipboard, and reduces empty-selection glitches. Workflow input fidelity. App context and pre-captured selection/clipboard are handed through more consistently when running workflows or launching previews, tightening “what you see is what you send.” Proxy-safe search tools. Brave Search and Google PSE tools now use a secure connection.

BoltAI 2.2.1

Workflow hotkeys. Assign global shortcuts to individual workflows and trigger them from anywhere; we pre-capture selection/clipboard so runs stay reliable without polluting your pasteboard. Inline workflow AI output. Workflows can now generate answers directly using your configured provider/agent before applying output actions, with smarter provider/model resolution and safer selection capture; agent-specific settings are now respected. Workflow Palette polish. New headless mode for “no preview” workflows, Ctrl+N/Ctrl+P navigation, direct preview launch for a chosen workflow, and clearer progress overlay while runs complete. Shortcut defaults & onboarding tweaks. Updated defaults (Option+Space to toggle the app, Control+Space for the Workflow Palette), better support for alternate keyboard layouts (Dvorak, etc.), plus small onboarding refinements and OAuth reliability improvements. Temporary chat promotion. You can now convert a temporary chat into a normal, synced conversation from the Conversation menu. MCP connectors logging. Added richer logging around MCP/OAuth flows for easier troubleshooting.

BoltAI 2.2.0

• New: Connectors (remote MCP servers). Browse a curated catalog of official MCP connectors (Notion, Linear, Todoist, Supabase, Sentry, and more), sign in via OAuth, and keep your connections synced with BoltAI Cloud—or add your own custom MCP servers when your provider isn’t listed.
• New: Inline Workflows & Workflow Palette. Highlight text in any app, hit your Workflow Palette shortcut, pick a saved workflow, and BoltAI will run it using your selection or clipboard and paste the answer back into the frontmost app, with flexible input/output behaviors you can customize.
• Improved: Agent & workflow management. Manage large libraries more easily with bulk-edit tools for agents and workflows, plus a smoother quick-add flow and workflow preview polish.
• Fixes & reliability. Improved sync stability, more robust imports from older BoltAI data that sometimes lacked text parts, better handling of reasoning settings for custom providers, and many small UI and performance refinements across MCP, workflows, and settings.

BoltAI 2.1.2

• New Feature: ShotSolve. Screenshot to Answers: capture your screen and get explanations, fixes, or summaries in seconds.
• New. Edit assistant messages to fine-tune the response.
• Improved. Refresh Codex CLI auth tokens in Settings > AI Services > Codex CLI.
• Improved. Codex CLI now supports newer models: GPT-5.1 and GPT-5.1 Codex models.
• Improved. Preview HTML code blocks right within BoltAI.