Changelog.

AI writing and editing got much more reliable

• The AI can now edit rich note content much better, including headings, checklists, bold/italic, links, separators, tables, and inline note/link pills.
• Mermaid diagrams and math blocks are handled more safely, with better create-vs-update behavior so the AI is less likely to insert raw code when you wanted a rendered block.
• Wiki links and link pills are now more resilient (including auto-recovery when metadata is missing), so they behave more like manually created links.
• Attachment reading is more robust: the AI is better at resolving the correct attached file even when it only has a visible filename.
• The AI now avoids “fake completion” cases where it claims content was added without actually writing to the note.

Read all the notes

Better AI run experience

• Clearer AI run status/progress visibility while a task is in flight.
• Improved cancellation handling so stopping generation is more predictable and immediate.
• Better persistence guidance and behavior around generated file content.

Voice features improved

• Added local speech-to-text and text-to-speech workflow with better focus-aware behavior.
• Read-aloud now has a toggle-style stop action, so stopping playback is faster and more intuitive.

Notebook experience improved

• Markdown cells now render LaTeX math expressions better.
• Math formatting in notebook markdown is auto-normalized for cleaner output.
• Auto-scroll now keeps AI-edited notebook cells in view after updates.

UI and app behavior improvements

• Update notifications now include direct changelog links.
• File tree/recent activity refresh behavior is more consistent and timely.
• Fixed an issue where switching tabs could incorrectly trigger edit events.

Overall quality

• Large round of reliability hardening for agent tool calls and edge cases.
• Improved guardrails and fallback behavior across advanced edit flows to reduce confusing outcomes.

Better editing for diagrams and formulas

• You can now edit existing Mermaid diagrams directly, and your updates are saved reliably.
• You can now edit inline math more easily through a dedicated editing flow.
• Mermaid and math blocks now show a clear hover edit badge, so it’s easier to discover where to click.

Smarter, more consistent AI chat behavior

• AI chat history is now separated per document, so conversations don’t get mixed between notes.
• AI generation progress is preserved per document when switching tabs, making multitasking smoother.
• Mermaid and math-related AI tools were improved, with more stable behavior and friendlier Mermaid error handling.

UI polish

• File tree and secondary sidebar layout were refined for a cleaner, more consistent look.

New Model: SmolLM3 3B

• Built for 8 GB Macs — A new 1.9 GB model that runs comfortably on base-model MacBooks. It rivals Qwen 3 4B in quality at a smaller footprint, with full support for thinking and tool use.

Better Model Recommendations

• "Recommended" badge is now realistic — The model picker used to recommend the biggest model your total RAM could theoretically hold, ignoring that macOS and other apps are already using several gigabytes. It now accounts for OS overhead and recommends a model that will actually run with comfortable headroom for the KV cache.

AI Agent Improvements

• Agent now writes into your notes instead of just chatting — When you ask the agent to "write a summary" or "draft a project update," it now uses write tools to put the content directly into your note. Previously it would sometimes just dump the text into the chat panel, which wasn't useful.
• Better cross-note research — When the agent searches your notes and needs to synthesize content from them, it now reads the full text of each note before writing. Previously it would sometimes work from 150-character snippets, producing shallow or inaccurate results.

AI Model Loading

• Fixed crashes on machines with limited memory — The AI engine now accounts for how much memory the model itself uses before deciding on a context window size. Previously it only looked at total system RAM, which caused "too large for available VRAM" errors for many users — especially when loading larger models on 16 GB or 24 GB Macs.
• Smarter memory usage — Removed an unnecessary 4x memory overhead from the AI context allocation. Models now load with a much smaller memory footprint, leaving more room for the rest of your system.
• Graceful fallback when memory is tight — If the AI engine can't fit the ideal context window into memory, it will automatically try smaller sizes (up to 3 times) instead of crashing outright. You'll still get a working AI — just with a shorter conversation memory for that session.
• Clearer error messages — If a model truly can't fit on your hardware, the error now tells you plainly that the model is too large, instead of showing a cryptic internal message.

Keyboard Navigation

• Quick tab switching — Press Ctrl+Tab to jump to the next open tab and Ctrl+Shift+Tab to go back. This works across all split panes, so you can cycle through every open note in one smooth loop.

AI Agent

• Smarter note editing — The agent now uses a more reliable find-and-edit workflow when making changes to your notes, reducing the chance of edits landing in the wrong spot.
• Cleaner conversations — The agent no longer leaks internal tool syntax into its responses. Conversations read more naturally, without cryptic bracket codes showing up mid-reply.
• No more 30-second timeout — When the agent proposes a change and waits for your approval, it will now wait as long as you need. Previously it would time out after 30 seconds.
• Better change previews — The diff review panel now shows richer descriptions for insertions and full-content replacements, making it easier to understand what the agent wants to change before you approve.
• Improved search accuracy — When the agent searches your note for a specific section, markup tags are now stripped so searches like "FAQ" match correctly even if the heading has formatting.

Real-Time AI Streaming

• AI responses now appear directly in your note as they're being written — you can watch your content take shape in real time instead of waiting for the full result
• Works for all AI actions: insertions, rewrites, and selection replacements
• The AI modal stays minimal during generation — just "Writing..." with a cancel button — while content streams into the editor behind it

Read all the notes

Smarter AI Agent

• The AI chat agent is now significantly more reliable when editing your notes — tool calls are validated at the inference level, eliminating malformed or broken edits
• Added a new find-and-replace editing capability so the agent can make targeted changes to specific sections without affecting the rest of your document
• The agent now handles longer, multi-step tasks more gracefully with improved execution controls

Unified AI Experience

• The AI modal (Cmd+K) now works identically for both notes and notebooks — same interface, same streaming behavior, same keyboard shortcuts
• New "Open Chat Panel" button in the AI modal lets you seamlessly hand off a prompt to the full agent chat when you need a more conversational interaction
• Cleaner error messages when AI is busy — instead of a cryptic error, you'll see a friendly "AI is busy with another task" notice

Notebook Improvements

• Redesigned markdown cells with a structured header bar matching code cells — drag handles, cell indices, and inline toolbar controls are now consistent across cell types
• New notebook settings panel: configure run-all scroll speed and delay between cells
• Package manager now includes a "Delete All" button to quickly clear installed Python packages
• Smarter run-all execution: the view scrolls to each cell's output as it completes
• Consistent 1-based cell numbering across all cell types

Under the Hood

• Major internal cleanup: removed thousands of lines of legacy workaround code
• Improved tag cleanup when deleting notebooks — usage counts and orphan tags are now handled correctly
• Better Python kernel package handling with more reliable install defaults

Improvements

• More readable AI modals — The AI prompt panels (in both notes and notebooks) are now easier to read. The glassmorphic background is slightly more opaque so text and buttons no longer blend into the content behind them.

0.1.0-beta.6

Notebooks

• AI now sees your attached files. When you ask the notebook AI for help, it knows which files you've uploaded and can suggest the right code to use them (e.g. librosa.load('song.mp3'), pd.read_csv('data.csv')).
• AI knows how to save files back. The AI can now guide you through using save_to_notebook() to save outputs — DataFrames, JSON, images, or any file — back to the notebook as attachments.
• Fixed Run button animation. Running an individual cell now properly shows the spinning "Running..." indicator. Previously this only worked with Run All.
• Package manager now hints at version pinning. The install field placeholder shows numpy==1.26.4 as an example so you know you can pin specific versions.

Editor

• Fixed autocomplete overlapping with placeholder text. The ghost-text autocomplete no longer triggers when the cursor is on an empty line, preventing it from rendering on top of the "Start writing..." placeholder.