Changelog

v1.33.0

• New: Added support for Claude 3.7 Sonnet
• Improved: Added support for reasoning models on OpenRouter
• Improved: Better cache breakpoint handling for Anthropic models
• Other bug fixes and improvements

What's new?

The most notable change in this release is supporting Anthropic's new Claude 3.7 model. This new model allows you to set a custom "thinking budget tokens". You can decide how hard the model think.

BoltAI simplifies this by using the same Reasoning Effort setting:

• Low: 4K thinking tokens
• Medium: 16k thinking tokens
• High: 32k thinking tokens

It's recommended to start with medium (16k tokens) as it's the optimal setting when using Claude 3.7 extended thinking.

v1.32.3 (build 150)

• New: Added support for Github Marketplace, Pico AI Homelab (MLX), Cerebras AI.
• New: Fetch model lists for Custom AI services.
• Improved: o1 models now support streaming.
• Improved: Copy reasoning content to clipboard.
• Improved: Better error handling for AI services.
• Improved: Better Advanced Voice Mode.

v1.32.0 build 146

• New: Added support for OpenAI's reasoning_effort parameter
• New: Added support for OpenRouter's reasoning content.
• Fixed: Projects not showing all AI models.

v1.31.0 build 144

• New: Added support for citations when using Perplexity or Web Search AI Plugins.
• New: Show AI Plugin input params if available.
• New: Chats within projects now support drag-and-drop and other operations.
• Fixed: o1 doesn't work with custom GPT parameters.
• Fixed: Cannot setup a new Anthropic service

v1.30.5 (build 143)

• New: Added support for the new DeepSeek Reasoning model.
• New: Thinking UI. Show reasoning content in a popover.
• Improved: Automatically pulls the model list from DeepSeek platform.
• Improved: Automatically loads previous chat messages on second page.
• Fixed: Alt AI Command profile not showing up.
• Fixed: Jumpy scroll experience.
• Fixed: Always enable text selection for user messages.
• Fixed: Floating window feature doesn't work for some users.
• Other bug fixes and improvements.

v1.30.3 (build 141)

• New: Revamped the model selection UI, both in the navigation bar and in the chat settings.
• New: Swipe gestures in chat list. Swipe left to archive & delete, swipe right to star
• New: Supports "true floating" settings for New Chat & New Temporary Chat windows. Find it in Settings → Shortcuts.
• New: Better keyboard shortcuts support. Select next/previous chat with Command+Shift+[ or Command+Shift+]. Select pinned chat with Command+1 to Command+9
• Fixed: o1 model not working (streaming flag must be turned off)
• Fixed: Image sharing showing incorrect model
• Improve scroll performance

v1.30.2 Happy New Year

Happy New Year! This is a big update with many improvements.

• BoltAI Projects: Projects keep chats, files, and custom instructions in one place.
• New: Official support for the DeepSeek platform.
• Better support for Amazon Bedrock: you can set AWS_SESSION_TOKEN, or use your aws credentials profile
• Significant improvement to the sidebar performance and stability.
• Improved search UI: global search bar on the sidebar and local findbar on each chat.
• Improved the Plugin List UI.
• Improved the Chat's System Instruction Configuration UI.
• Improved: You can re-order and bulk delete AI Services now
• Fixed the issue where Gemini 2.0 Flash model cannot use Grounding Tool
• Removed the "Context Length" requirement for Custom Server
• Fixed the issue where BoltAI's sending empty system instruction
• Fixed the issue where O1 models not showing up for some users
• Fixed other crashes related to the sidebar
• Fixed the issue where AI Inline doesn't work with Dvorak QWERTY ⌘ layout
• Fixed crashes related to a SwiftUI bug on macOS 12

Read full release note: https://boltai.com/blog/boltai-projects-deepseek-support-and-more

v1.29.4: bug fixes & improvements

This release focuses on bug fixes and other improvements

• Fixed: chat streaming freezes or is very slow
• Fixed: gpt inline trigger doesn't work if OpenAI is not the default service
• Fixed: AI Command pallete doesn't stay on top
• Fixed: not discovering beta updates
• Attemp to fix the issue where BoltAI would crash when going back from background
• Fixed the issue where prompt stuck in "continue mode"

v1.29.0: Amazon Bedrock & xAI support, cache breakpoint and more

• Official supports for Amazon Bedrock & xAI
• Set custom cache breakpoint when using Anthropic models
• Convert temporary chat to normal chat
• Added support for o1 models on Azure
• Document Analysis now supports for more file types
• Improved scroll-to-bottom behavior, faster list view
• Improved drag-and-drop experience
• Fixed the issue where control+n / control+p for non-standard keyboard layout
• Fixed the issue where app icon is reverted after update
• Fixed issue where cannot set up Advanced Voice Mode without OpenAI API key
• Fixed issue with Web Search plugin for some Anthropic users

You can read the full release note here: https://boltai.com/blog/amazon-bedrock-and-xai-support-cache-breakpoint-and-more

v1.28.1: Improved AI Command

This release improves the AI Command experience

• Improved the AI command keyboard handling. You can now use control+n or control+p to navigate.
• Improved input handling for Japanese input source
• Improved AI Command performance, faster search & scrolling
• Fixed an issue with toggling the AI Command window