Releases: FuJacob/cotabby
Cotabby 0.4.2-beta
🚀 Cotabby 0.4.2-beta
This is one of Cotabby’s biggest quality releases yet.
Cotabby 0.4.2-beta focuses on making completions feel faster, cleaner, safer, and more useful in real writing. This release upgrades emoji autocomplete, adds tighter suggestion-length controls, improves OCR visual context, hardens model downloads, and lays the groundwork for a stronger open-source base-model pipeline.
✨ Headline Features
😄 Smarter emoji autocomplete
Emoji completion is now much more natural. Cotabby now supports recents, synonyms, fuzzy matching, and popularity ranking, so partial inputs like :smil, :party, :thanks, or :+1 are more likely to return what you actually meant.
⚡ New 2–4 word suggestion preset
A new short suggestion preset gives you tighter, lower-distraction completions when you want Cotabby to stay fast and lightweight.
🛡️ Better completion safety
Cotabby now applies stronger last-mile output safety gates before showing ghost text. These help suppress duplicated text, unsafe insertions, awkward sentence-boundary issues, and completions that do not fit the current field.
🧠 Stronger local model foundation
This release includes major internal work toward Cotabby’s open-source base-model path, including:
- Prompt budgeting
- Token-aware context handling
- Constrained decoding experiments
- Beam search
- Vocabulary profile caching
- Fill-in-middle prompting
- Better empty-completion diagnostics
Some of this remains behind feature flags, but the foundation is much stronger.
👁️ Cleaner visual context
Visual-context OCR is now simpler and more reliable. Cotabby removed the old LLM-based OCR summarizer path and replaced it with direct OCR hygiene filtering, including per-line confidence handling.
Result: a faster, cleaner, less fragile context pipeline.
⚙️ Better app controls
Cotabby now includes:
- Open at Login toggle
- Performance settings pane with opt-in latency tracking
- Better menu bar and Settings behavior
- Reduced AX capability flicker
- Safer handling around secure fields
- Fixes for Calendar popovers and overlay crashes
🔒 Hardened model downloads
Model download integrity checks are now stronger, helping protect users from incomplete or corrupted model downloads.
🐛 Notable Fixes
- Fixed rapid
Tabsometimes leaking into the host app after accepting the final word. - Fixed focus polling dismissing Calendar’s event popover.
- Fixed an overlay crash found during pre-release audit.
- Fixed dead settings and dead visual-context state.
- Fixed broken test scaffolding after visual-context cleanup.
- Fixed constrained-decoder latency regressions by bounding top-K work and skipping unused computation.
- Reverted constrained decoder as the only llama decode path after testing showed it was not ready to fully replace the existing path.
📦 Full Changes
- Update README by @FuJacob in #474
- Add Performance settings pane with opt-in LLM latency tracking by @jkrauska in #471
- Add 2-4 word length preset by @FuJacob in #480
- Add Open at Login toggle to General settings by @FuJacob in #450
- Dismiss menu bar popover when opening Settings by @jkrauska in #481
- Fix rapid Tab leaking into the host after a final-word accept by @FuJacob in #484
- Output safety gates: dedup, insertion safety, sentence boundary by @FuJacob in #485
- Stop focus polling from dismissing Calendar's event popover by @FuJacob in #483
- Improve visual context OCR quality by @FuJacob in #482
- Bump suggestion token budgets down to track word presets by @FuJacob in #493
- Add base-model completion pipeline behind a default-off flag by @FuJacob in #495
- Suppress AX capability flicker on the same focused element by @FuJacob in #494
- Smarter emoji completion: recents, synonyms, fuzzy matching, popularity by @FuJacob in #496
- Cotabby 2: cut the Open Source path to base models by @FuJacob in #497
- Budget the base prompt by section by @FuJacob in #498
- Replace the LLM OCR summarizer with direct OCR-hygiene filtering by @FuJacob in #499
- Fix CotabbyTests build broken by #499 by @FuJacob in #500
- Remove the dead visual-context summarize path by @FuJacob in #501
- Add deterministic constrained decoder behind a default-off flag by @FuJacob in #503
- Add no-repeat-ngram repetition guard to the constrained decoder by @FuJacob in #504
- Re-tune onboarding model recommendations for the base-model tiers by @FuJacob in #505
- Surface per-line OCR confidence so the low-confidence filter runs by @FuJacob in #506
- Remove the dead summarizing-text visual-context state by @FuJacob in #509
- Remove dead code surfaced by a whole-app audit by @FuJacob in #511
- Refresh docs for the base-model migration by @FuJacob in #512
- Keep the KV cache on cancelled llama generations by @FuJacob in #513
- Collapse the Open Source catalog to four named tiers by @FuJacob in #514
- Accept one word at a time in space-less scripts by @FuJacob in #515
- Catch more secure fields: role description and non-password secrets by @FuJacob in #516
- Stop the constrained decoder at sentence boundaries by @FuJacob in #517
- Add multi-branch beam search to the constrained decoder by @FuJacob in #518
- Cache the constrained-decode vocabulary profile on disk by @FuJacob in #519
- Make the constrained beam finish the current word mid-word by @FuJacob in #520
- Add fill-in-middle prompting for mid-line completions by @FuJacob in #521
- Log why a completion normalized to empty by @FuJacob in #522
- Gate fill-in-middle on a precise end-of-line signal by @FuJacob in #523
- Document how to evaluate the experimental decoder on device by @FuJacob in #524
- Add required-prefix admissibility to the constrained beam decoder by @FuJacob in #526
- Add per-site disable rules to the availability gate by @FuJacob in #527
- Add an execution-ready plan for the remaining parity work by @FuJacob in #528
- Make per-site disable live: capture the focused page URL by @FuJacob in #529
- Add opt-in clipboard paste insertion for long completions by @FuJacob in #530
- Add token-aware prompt budgeting as an opt-in path by @FuJacob in #531
- Make the constrained decoder the only llama decode path by @FuJacob in #532
- Hide custom rules from users behind a feature gate by @FuJacob in #533
- Fix three bugs found in a pre-release audit by @FuJacob in #534
- Fix an overlay crash and two dead settings by @FuJacob in #535
- Harden model download integrity by @FuJacob in #536
- Match Extended Context cap to what the engine actually uses by @FuJacob in #537
- Fix constrained-decode latency by @FuJacob in #538
- Revert constrained decoder as the only llama decode path by @FuJacob in #539
🔗 Changelog
Full Changelog: v0.4.1-beta...v0.4.2-beta
Cotabby 0.4.1-beta
0.4.1-beta Hotfix
- Fixed high CPU usage and typing lag in very large text fields by coalescing stale Accessibility polling chains and reading only the caret-adjacent text window.
Hotfix Changelog: v0.4.0-beta...v0.4.1-beta
Welcome to Cotabby 0.4.0-beta! This release delivers major quality-of-life upgrades: a new inline emoji picker, granular acceptance controls, massive latency cuts, and a revamped onboarding flow.
🚀 Headline Features
- Inline Emoji Picker: Native
:emoji:picker with skin tone/gender customization, smart hover states, and reliableTabcommit. - Granular Acceptance Controls: Accept suggestions exactly how you want—by Word, Phrase, or Full completion.
- Extended Context Playground: New Advanced settings pane to test and visualize how context feeds into the AI engine.
- Chromium & Electron Support: Expanded macOS accessibility to fully support autocomplete in Chromium-based web editors.
⚡ Performance & AI Engine
- Slashed Latency: Drastically reduced typing delay with aggressive optimizations (50ms polling, 20ms debounce).
- Cleaner AI Output: The engine now automatically strips hallucinated prompt-scaffolding labels from suggestions.
- Stable Ghost Text: Fixed ghost font rendering glitches by locking it to field identity instead of focus sequence.
✨ UX & Settings Polish
- Revamped Onboarding: Redesigned out-of-the-box flow with starting templates, grid layouts, and a live autocomplete showcase.
- Settings Overhaul: Flattened the sidebar, unified the Engine & Model panes, and added helpful subtext for complex options.
- Global Hotkeys: Added a global toggle hotkey to enable/disable Cotabby, plus built-in safeguards to prevent shortcut conflicts.
- UI Cleanup: Fixed popup borders, removed redundant toggles, and added an option to hide the word-count badge for a cleaner menu bar.
New Contributors
- @rpickmans made their first contribution in #388
- @jkrauska made their first contribution in #425
0.4.0 Changelog: v0.3.3-beta...v0.4.0-beta
Cotabby 0.4.0-beta
Welcome to Cotabby 0.4.0-beta! This release delivers major quality-of-life upgrades: a new inline emoji picker, granular acceptance controls, massive latency cuts, and a revamped onboarding flow.
🚀 Headline Features
- Inline Emoji Picker: Native
:emoji:picker with skin tone/gender customization, smart hover states, and reliableTabcommit. - Granular Acceptance Controls: Accept suggestions exactly how you want—by Word, Phrase, or Full completion.
- Extended Context Playground: New Advanced settings pane to test and visualize how context feeds into the AI engine.
- Chromium & Electron Support: Expanded macOS accessibility to fully support autocomplete in Chromium-based web editors.
⚡ Performance & AI Engine
- Slashed Latency: Drastically reduced typing delay with aggressive optimizations (50ms polling, 20ms debounce).
- Cleaner AI Output: The engine now automatically strips hallucinated prompt-scaffolding labels from suggestions.
- Stable Ghost Text: Fixed ghost font rendering glitches by locking it to field identity instead of focus sequence.
✨ UX & Settings Polish
- Revamped Onboarding: Redesigned out-of-the-box flow with starting templates, grid layouts, and a live autocomplete showcase.
- Settings Overhaul: Flattened the sidebar, unified the Engine & Model panes, and added helpful subtext for complex options.
- Global Hotkeys: Added a global toggle hotkey to enable/disable Cotabby, plus built-in safeguards to prevent shortcut conflicts.
- UI Cleanup: Fixed popup borders, removed redundant toggles, and added an option to hide the word-count badge for a cleaner menu bar.
New Contributors
- @rpickmans made their first contribution in #388
- @jkrauska made their first contribution in #425
Full Changelog: v0.3.3-beta...v0.4.0-beta
Cotabby 0.3.3-beta
Cotabby 0.3.2-beta
Hotfix: input swallowing
If you were on 0.3.0-beta and noticed that typing in Chrome, Slack, Discord, or other Electron / Chromium-based apps sometimes felt like Cotabby was eating your keystrokes — this build fixes that.
What was happening
While a Cotabby suggestion was visible, the OS-level accept-key hook could swallow keystrokes that matched the user's accept binding. The match logic was correct in isolation, but two structural holes made it possible for ordinary typing to disappear:
- The key recorder accepted bare alphanumerics like a plain letter as an accept binding. From that moment, every press of that letter system-wide while a suggestion was visible got eaten.
- The default full-accept binding was bare backtick (`) — a real character users type in code, markdown, and JS template literals.
- The hook had no in-the-moment check that a real, ready suggestion existed when it consumed; any stale lifecycle state could leak into a swallow.
What changed
The active accept tap is now fail-open (#382). It refuses to consume a keystroke when either of the following is true:
- The bound key is a bare printable (no modifier + produces a unicode character). A warning lands in the runtime log pointing at Settings > Shortcuts.
- The coordinator does not confirm at event time that the suggestion state is
.ready, an active session is live, and the overlay is visible.
When in doubt, the keystroke falls through to the host app unchanged. The legitimate accept path is unchanged: with a modified binding (or plain Tab) and a real ready suggestion, acceptance still fires exactly as before.
Notes
- If you previously recorded a bare letter as your accept key, rebind it with a modifier in Settings > Shortcuts to restore acceptance. The fix means your typing comes through either way; the warning in the log is the only hint.
- 0.3.1-beta was skipped: it bundled a tighter AX-publish timing tweak that turned out to regress prediction quality. That change is reverted here in #384.
Full Changelog: v0.3.0-beta...v0.3.2-beta
Cotabby 0.3.0-beta
What's Changed
- Fix CI: add missing CaretGeometrySelector type referenced by tests by @FuJacob in #322
- Replace 'App:' prompt prefix with natural-language phrasing by @FuJacob in #333
- Stop CGEvent tap from gating keystrokes in unrelated apps (#328) by @FuJacob in #337
- Hide the custom indicator icon picker from Settings by @FuJacob in #338
- Allow modifier keys in accept shortcuts (⇧Tab, ⌥Tab, …) by @FuJacob in #341
- Force all users back to the default indicator icon by @FuJacob in #343
- Fix accept keybind swallowing keystroke during background refresh by @FuJacob in #345
- Add mirror overlay fallback for unreliable caret geometry by @FuJacob in #347
- Bring tooltips back on macOS 26 beta + show accept key as a keycap by @FuJacob in #350
- Synthesize boundary space when accept would glue the suggestion onto the user's last word by @FuJacob in #348
- Hold overlay position across post-accept AX reconciles by @FuJacob in #349
- Cancel llama autocomplete generation when the wrapping Task is cancelled by @FuJacob in #346
- Let users toggle popup-card suggestion display from Settings and the menu by @FuJacob in #351
- Update Support section copy and CTA by @FuJacob in #352
- Retire SmolLM-360M and rename tabby-pico → tabby-nano-2 by @FuJacob in #355
- Expand FM eval suite: per-category scoring and latency by @FuJacob in #335
- Reuse FM LanguageModelSession and prewarm on focus change by @FuJacob in #336
- Stop regenerating suggestion on Enter so post-Enter actions aren't masked by @FuJacob in #359
- Reframe FM instructions positively and trim few-shots to two by @FuJacob in #342
- Remove the tooltip feature entirely by @FuJacob in #362
- Send FM trailing context, length hint, per-app tone, bigger prefix budget by @FuJacob in #344
- Scaffold redesigned Settings: sidebar container behind feature flag by @FuJacob in #356
- Replay swallowed Tab when coordinator bails on acceptance by @FuJacob in #363
- Add General / Permissions / About panes to redesigned Settings by @FuJacob in #364
- Add Engine & Model parent and Apple Intelligence / Open Source sub-panes by @FuJacob in #365
- Add Writing / Shortcuts / Apps panes to redesigned Settings by @FuJacob in #366
- Surface sidebar attention dots and flip Settings redesign default on by @FuJacob in #367
- Anchor user-forced popup card to the caret line, not the field rect by @FuJacob in #368
- Pin Settings sidebar visibility so the toolbar toggle stops teleporting by @FuJacob in #369
- Group Settings General into cards, surface Fast Mode + clarify context cost by @FuJacob in #370
- Give every Settings pane a consistent top inset by @FuJacob in #371
- Rename built-in models to the tabby-1-* family by @FuJacob in #372
- Inset Settings sidebar top and widen the column by @FuJacob in #373
- Larger Settings window, wider sidebar, align sidebar top with detail by @FuJacob in #374
- Tighten Settings sidebar width and restore its top inset by @FuJacob in #375
- Delay post-divergence prediction so Chromium AX can catch up by @FuJacob in #376
- Widen Settings sidebar and label the orphan About section by @FuJacob in #377
- Apply Chromium AX-publish delay to no-session keystroke path by @FuJacob in #378
- Wait for host AX publish before rescheduling, not a fixed 150ms by @FuJacob in #379
Full Changelog: v0.2.0-beta...v0.3.0-beta
What's Changed
- Fix CI: add missing CaretGeometrySelector type referenced by tests by @FuJacob in #322
- Replace 'App:' prompt prefix with natural-language phrasing by @FuJacob in #333
- Stop CGEvent tap from gating keystrokes in unrelated apps (#328) by @FuJacob in #337
- Hide the custom indicator icon picker from Settings by @FuJacob in #338
- Allow modifier keys in accept shortcuts (⇧Tab, ⌥Tab, …) by @FuJacob in #341
- Force all users back to the default indicator icon by @FuJacob in #343
- Fix accept keybind swallowing keystroke during background refresh by @FuJacob in #345
- Add mirror overlay fallback for unreliable caret geometry by @FuJacob in #347
- Bring tooltips back on macOS 26 beta + show accept key as a keycap by @FuJacob in #350
- Synthesize boundary space when accept would glue the suggestion onto the user's last word by @FuJacob in #348
- Hold overlay position across post-accept AX reconciles by @FuJacob in #349
- Cancel llama autocomplete generation when the wrapping Task is cancelled by @FuJacob in #346
- Let users toggle popup-card suggestion display from Settings and the menu by @FuJacob in #351
- Update Support section copy and CTA by @FuJacob in #352
- Retire SmolLM-360M and rename tabby-pico → tabby-nano-2 by @FuJacob in #355
- Expand FM eval suite: per-category scoring and latency by @FuJacob in #335
- Reuse FM LanguageModelSession and prewarm on focus change by @FuJacob in #336
- Stop regenerating suggestion on Enter so post-Enter actions aren't masked by @FuJacob in #359
- Reframe FM instructions positively and trim few-shots to two by @FuJacob in #342
- Remove the tooltip feature entirely by @FuJacob in #362
- Send FM trailing context, length hint, per-app tone, bigger prefix budget by @FuJacob in #344
- Scaffold redesigned Settings: sidebar container behind feature flag by @FuJacob in #356
- Replay swallowed Tab when coordinator bails on acceptance by @FuJacob in #363
- Add General / Permissions / About panes to redesigned Settings by @FuJacob in #364
- Add Engine & Model parent and Apple Intelligence / Open Source sub-panes by @FuJacob in #365
- Add Writing / Shortcuts / Apps panes to redesigned Settings by @FuJacob in #366
- Surface sidebar attention dots and flip Settings redesign default on by @FuJacob in #367
- Anchor user-forced popup card to the caret line, not the field rect by @FuJacob in #368
- Pin Settings sidebar visibility so the toolbar toggle stops teleporting by @FuJacob in #369
- Group Settings General into cards, surface Fast Mode + clarify context cost by @FuJacob in #370
- Give every Settings pane a consistent top inset by @FuJacob in #371
- Rename built-in models to the tabby-1-* family by @FuJacob in #372
- Inset Settings sidebar top and widen the column by @FuJacob in #373
- Larger Settings window, wider sidebar, align sidebar top with detail by @FuJacob in #374
- Tighten Settings sidebar width and restore its top inset by @FuJacob in #375
- Delay post-divergence prediction so Chromium AX can catch up by @FuJacob in #376
- Widen Settings sidebar and label the orphan About section by @FuJacob in #377
- Apply Chromium AX-publish delay to no-session keystroke path by @FuJacob in #378
- Wait for host AX publish before rescheduling, not a fixed 150ms by @FuJacob in #379
Full Changelog: v0.2.0-beta...v0.3.0-beta
Cotabby 0.2.0-beta
Cotabby v0.2.0-beta
This release focuses on performance, stability, customization, and making Cotabby feel better across more macOS apps.
A lot of the commits in this release were small bug fixes, cleanup changes, or quick reverts, so this summary groups the meaningful changes instead of listing every commit one by one.
Highlights
-
Lower idle CPU usage
- Reduced background polling in browser and Electron apps.
- Debounced visual context updates.
- Fixed indeterminate
ProgressViewspinners that could keep CPU usage high.
-
New Fast Mode
- Added a Fast Mode toggle that skips the screenshot/OCR pipeline.
- Useful for users who want lower overhead and faster completions.
-
Better autocomplete behavior
- Tightened completion length budgets.
- Fixed double spaces when accepting suggestions.
- Added better word-boundary handling during insertion.
- Added an option to accept a word without also accepting trailing punctuation.
-
More flexible shortcuts
- Added support for binding any key as the accept shortcut.
- Added an option to hide the accept-key hint from suggestions.
-
More local model options
- Added
tabby-pico-1, the smallest default model. - Added
tabby-nano-1. - Added
tabby-max-1. - Updated the README model table with shipped models and community alternatives.
- Added
-
Hugging Face model browser
- Added a Hugging Face model browser to local model settings.
- Makes it easier to discover and manage compatible local models.
-
Better language support
- Added support for multiple writing languages using a soft prompt hint.
- Suggestions should behave better for users writing outside of English.
-
Improved caret placement
- Improved browser caret placement.
- Suggestions should appear more reliably near the cursor in supported browser text fields.
-
More customization
- Added ghost-text color controls.
- Added ghost-text opacity controls.
- Added support for a custom activation indicator icon.
-
Cleaner menu bar UI
- Grouped the menu bar popover into divider-separated sections.
- Trimmed less-used quick toggles from the popover.
- Added tooltips across Settings and menu bar quick controls.
-
Stability fixes
- Fixed a heap-corruption crash when deinitializing the caret geometry cache.
- Fixed flickering in the guided-permission helper during the permission granting flow.
- Removed the temporary menu-bar busy indicator after testing.
-
macOS 14 support
- Lowered the minimum macOS deployment target from macOS 15 to macOS 14.
-
Updates and packaging
- Added update checks on launch.
- Pinned Sparkle update checks to a daily interval.
- Added automatic Homebrew cask updates on release.
- Updated funding metadata.
-
Project infrastructure
- Added XcodeGen project configuration.
- Added checks to guard the generated Xcode project against drift.
- Documented the XcodeGen workflow.
-
Docs and repo cleanup
- Restyled the README header.
- Updated repo links to point at
FuJacob/cotabby. - Retitled the “Created by” section.
New contributors
- Thanks to @undivisible for their first contribution in #268.
Full Changelog: v0.1.1-beta...v0.2.0-beta
Cotabby 0.1.1-beta
What's Changed
Cotabby users may be experience some hanging/lag when on 0.1.0-beta, this restores gate for when AX tree is walked, as to reduce load. Focus polling also increased from 50ms to 80ms for performance.
Full Changelog: v0.1.0-beta...v0.1.1-beta
Cotabby 0.1.0-beta
What's Changed
- Replace word counter with Report and Check for Updates buttons by @FuJacob in #189
- Replace build number formula with github.run_number by @FuJacob in #190
- Skip OCR pipeline when Tabby is disabled globally or per-app by @FuJacob in #197
- Add full-suggestion acceptance keybind by @FuJacob in #198
- Rework menu bar: word count in icon, Report button in header, Check for Updates in footer by @FuJacob in #199
- Add structured logging with swift-log and Console.app support by @Jam-Cai in #200
- Fix external monitor geometry conversion by @Jam-Cai in #206
- Add manual GitHub Pages republish workflow by @FuJacob in #212
- Fix ggml_metal_rsets_free crash on app quit by @Jam-Cai in #191
- Rename project to Cotabby and replace LlamaSwift with CotabbyInference by @FuJacob in #202
- Update Package.resolved for remote CotabbyInference dependency by @FuJacob in #221
- Gitignore Package.resolved and .claude/worktrees/ by @FuJacob in #222
- Show accepted word count badge in menu bar icon by @FuJacob in #203
- Add Tabby → Cotabby rename transition reference by @FuJacob in #213
- Fall back to raw OCR text when summarization fails by @FuJacob in #219
- Add refresh button to menu-bar Model row by @FuJacob in #224
- Replace deferred termination with synchronous llama shutdown by @FuJacob in #225
- chore(deps): bump actions/checkout from 4 to 6 by @dependabot[bot] in #139
- Bump actions/deploy-pages from 4 to 5 by @dependabot[bot] in #140
- chore(deps): bump actions/setup-python from 5 to 6 by @dependabot[bot] in #141
- Bump actions/upload-pages-artifact from 3 to 5 by @dependabot[bot] in #142
- chore(deps): bump actions/upload-artifact from 4 to 7 by @dependabot[bot] in #143
- Add clipboard relevance filter and line-level distillation by @FuJacob in #210
- Skip event tap processing in terminals and disabled apps by @FuJacob in #201
- Route GGUF model discovery through LM Studio folder by @FuJacob in #217
- Add multi-line completion support with menu bar toggle by @FuJacob in #216
- Add CI check for Sparkle exact version pin by @FuJacob in #188
- Add file log handler gated behind -cotabby-debug by @FuJacob in #227
- Fix Sparkle pin verification path after project rename by @FuJacob in #231
- Fix README badge + clone URLs (repo is still FuJacob/tabby) by @FuJacob in #234
- Strip MLX functionality by @Jam-Cai in #230
- Rename all app UserDefaults keys to the cotabby prefix by @FuJacob in #238
- Default full-acceptance binding to the backtick key by @FuJacob in #228
- Add Support section with Buy Me a Coffee link by @FuJacob in #241
- Reorder menu bar toggles and clarify their labels by @FuJacob in #240
- Replace paw symbol with Cotabby cat logo across UI by @FuJacob in #237
- Refine Support section copy and donate button by @FuJacob in #242
- Move support section to top of README by @FuJacob in #243
- Add custom autocomplete rules (tags + suggestions) by @FuJacob in #239
- Switch update feed and Pages domain to updates.cotabby.app by @FuJacob in #232
- Polish: menu-bar language picker, Apple Intelligence drift fix, drop beta labels by @FuJacob in #244
- Try BoundsForRange optimistically for exact caret placement by @FuJacob in #218
- Add two more downloadable models (four defaults) by @FuJacob in #245
- Point sparkle:releaseNotesLink at the landing /release-notes/{tag} route by @FuJacob in #233
- Reorganize settings by task and reconcile with the menu bar by @FuJacob in #246
- Left-align README support block and drop top divider by @FuJacob in #247
- Stabilize ghost-text size per focus session by @FuJacob in #250
- Stabilize ghost-text size, token-budget completion length, tabby model lineup, full-accept reset by @FuJacob in #251
- Materialize Package.resolved before reading the Sparkle pin in release by @FuJacob in #252
New Contributors
- @dependabot[bot] made their first contribution in #139
Full Changelog: v0.0.6-beta...v0.1.0-beta
tabby 0.0.6-beta
What's Changed
Full Changelog: v0.0.5-beta...v0.0.6-beta