Cumbersome Changelog

• feat(settings): simplify AI connections and configuration
• fix(settings): enable headless mode by default
• fix(mac-chat): avoid model picker popovers on macOS 27
• fix(privacy): gate iCloud Drive diagnostics to debug
• fix(mac-chat): defer selection until model picker dismisses
• fix(ios-chat): stabilize VoiceOver composer focus
• fix(mermaid): retain WebKit renderer session
• perf(mac-chat): reduce long-transcript scroll stalls
• perf(latex): move equation rendering off the main thread
• refactor(settings): collapse provider details and simplify MCP
• refactor(settings): unify conversation retention policy
• refactor(browser): make headless mode govern parallel tools
• refactor(settings): remove redundant on-device copy
• refactor(mcp): enable bounded parallel execution by default

• feat(annotations): add conversation passage notes
• feat(read-aloud): add playback and voice guidance
• feat(mermaid): render fenced diagrams automatically
• feat(read-aloud): add spoken replies and auto-read
• fix(latex): stabilize macOS equation sizing
• fix(latex): pin MathJaxSwift after braced exponent regression
• fix(ios-chat): dismiss keyboard after message submission

• feat(markdown): add code block copy controls
• feat(mermaid): add offline diagram rendering
• feat(conversation-export): add Markdown export
• feat(chat-toolbar): make title the conversation actions menu
• feat(message-details): add request diagnostics
• feat(data-analysis): add on-device Python tool
• fix(ios-attachments): keep picker labels on one line
• fix(ios-chat): preserve conversation title width

• feat(providers): add custom Responses endpoints
• feat(gemini): add file-backed video uploads
• feat(settings): add current date context to AI requests
• fix(accessibility): stop auto-follow during VoiceOver review
• perf(local-browser): bound extraction work off main actor
• refactor(settings): centralize preference persistence

• fix(face-off): safely recover every legacy persistence shape
• fix(sidebar): retain footer backing above iOS keyboard
• fix(persistence): harden legacy message migration

• feat(mcp): add bounded parallel tool execution
• feat(local-tools): add bounded parallel headless execution
• feat(chat-ui): refine conversation actions and navigation
• fix(face-off): recover legacy messages without SwiftData crashes
• fix(find): highlight matches without strikethrough
• fix(chat): preserve compaction and attachment ownership
• fix(chat): preserve partial streams and navigate find matches
• fix(mac-chat): target the realized transcript tail
• fix(mac-chat): preserve streams and guard restart popovers
• fix(mac-chat): stabilize long transcript scrolling
• fix(tools): preserve valid streamed tool names
• fix(tools): decode quoted search summaries correctly
• fix(markdown): refresh LaTeX renderer when input changes
• fix(ios-navigation): restore hamburger menu taps
• fix(chat-ui): clarify token usage accounting
• fix(mind-meld): stabilize iOS model configuration
• fix(mind-meld): refine macOS configuration disclosure

• feat(ios-chat): show conversation title in toolbar
• feat(macOS): show conversation title in toolbar
• feat(chat): modernize transcript message presentation
• feat(chat): consolidate composer model selection
• feat(sidebar): modernize navigation controls
• feat(settings): relocate clear-all conversation action
• feat(chat): add adaptive multi-AI Mind/Meld synthesis
• fix(mac-chat): stabilize long transcript entry scroll

• feat(localization): add complete Simplified Chinese support
• feat(privacy): encrypt sensitive CloudKit fields for new records
• feat(chat): focus composer on New Chat across platforms
• fix(release): use Apple Git on Apple silicon
• fix(macos): restore composer file drag and drop
• fix(openrouter): replay stateless Responses tool history
• fix(macos): group controls in material toolbars
• fix(macos): rebalance chat toolbar controls
• fix(macos): refine chat and settings toolbars
• fix(chat): size message info popover for ADP footer
• fix(markdown): stop currency $ from swallowing headings and tables
• fix(privacy): Drive-back oversized tool and Face/Off payloads
• fix(chat): stream Ghost/Write drafts into the placeholder
• fix(providers): drop max_tokens from custom OpenAI titles
• fix(providers): decode Together-style custom models lists
• fix(macos): label Cmd-N as New Chat in File menu
• fix(chat): capture Compact confirm before sheet dismiss
• fix(chat): harden Compact cancel and drain pending queue
• chore(privacy): plan CloudKit ADP encryption
• perf(chat): throttle light streaming UI updates to ~20fps
• perf(chat): drop streaming dots TimelineView to ~12fps
• refactor(custom-params): drop duplicate JSONValidator helper

• feat(chat): import conversations from JSON on macOS
• feat(chat): add Ghost/Write
• fix(settings): preserve serif font and clarify local preferences
• fix(latex): pin SwiftDraw below 0.28 to restore equation images
• fix(chat): label MCP transcript rows as MCP, not local tools
• perf(chat): cache LaTeX parse/blocks across MarkdownTextView body evals
• perf(chat): avoid full collapse checks for row identity
• perf(chat): reduce long-transcript streaming CPU
• perf(chat): stop idle long-transcript CPU hangs
• perf(chat): avoid transcript refetches during streaming

• feat(chat): display streaming performance diagnostics
• feat(tools): remote MCP client with settings UI and tool routing
• feat(chat): include info-bubble metadata in Final JSON
• fix(core): replace expired Discord invite with new permanent link
• fix(chat): stop cloud models mimicking local tool transcript text

• feat(settings): theme picker and font options
• fix(ios-chat): stop transcript blanking when typing during stream
• fix(anthropic): request summarized thinking on adaptive models

• feat(chat): default-collapse local tool transcript rows with summaries
• feat(folders): add folder-level system message presets and editor
• feat(chat): assign draft new chats to folders before first send
• fix(latex): detect simple inline math without currency false positives
• fix(sidebar): adaptive bottom buttons for large Dynamic Type
• fix(ios-chat): anchor collapse/expand to the toggled row, not the bottom
• fix(vercel): route Anthropic thinking through providerOptions
• fix(local-browser): format local tool metadata as markdown bullets
• fix(local-browser): bound DOM snapshot timeout to unstick auto-extract
• fix(ios-chat): descramble scroll overlap without settle jump
• fix(chat): default thinking section collapsed during streaming
• refactor(core): replace regex HTML extraction with SwiftSoup
• style(ios-chat): inset message rows from screen edges
• style(chat): soften message row corners on iOS and macOS

• feat(vercel): unwrap nested stream errors
• feat(settings): default Anthropic prompt caching toggles on
• feat(chat): surface prompt-cache usage across providers
• feat(settings): add Anthropic prompt caching toggles
• fix(vercel): send PDF attachments in gateway file shape
• fix(gemini): send toolConfig and round-trip thought signatures
• fix(chat): gate send and streaming on global model selection
• fix(chat): descramble edited messages on iOS
• fix(chat): keep sibling thinking toggles clickable on macOS
• fix(chat): right-align RTL (Farsi/Arabic/Hebrew) markdown per block
• fix(icons): enable alternate app icons on iPad
• fix(chat): defer preset selection on draft new chat (iOS)

• feat(settings): add reusable system message presets per conversation
• feat(settings): offload long global system messages to iCloud Drive
• feat(settings): add toggle to pause custom API parameters

• feat(chat): option to compact conversation to reduce API context credits
• feat(settings): add Discord to About feedback support bullets
• fix(chat): stop ChatFindResponder republishing on every streaming frame
• fix(settings): stop model picker emptying on macOS/iOS sync
• perf(streaming): remove O(n²) chunk joins and per-token cost scans

• feat(chat): run HTML and JavaScript code blocks in WebView preview
• fix(chat): enable send when sole custom provider is selected
• fix(macos-chat): keep penultimate reply full until off screen on send
• fix(chat): resolve sends against the global model selection
• perf(sidebar): speed up drawer search and gate message highlights

• feat(settings): default local tools on and link to Tools tab
• feat(settings): OpenRouter PDF processing engine picker in Settings
• feat(settings): OpenRouter search picker in Settings
• feat(core): offload oversized message text to iCloud Drive
• fix(settings): show OpenRouter picker row labels on iOS
• fix(openrouter): migrate web search from deprecated plugin to server tool
• fix(ios-chat): stop post-send scramble when penultimate reply truncates
• fix(settings): make API key optional for OpenAI-compatible providers
• fix(ios-chat): descramble transcript on send via layout revalidation
• fix(macos): stop file-missing banner from blowing up window height
• build(deps): bump textual for empty table cell fix

• feat(onboarding): tighten API-key welcome copy and vendor list
• feat(about): personalize About tab and trim onboarding chrome
• feat(settings): organize Settings into Models/Tools/App/About tabs
• fix(ios-chat): stop transcript squash on send/delete/loading toggle
• fix(ios-chat): clear stale streaming indicator on previous assistant rows
• fix(ios-chat): stop transcript drift after breaking streaming auto-follow
• fix(core): omit reasoning_effort by default on customOpenAI chat
• fix(settings): match iOS About legal row typography to intro copy
• perf(chat): add extraHeavy streaming throttle tier and retune gates

• feat(local-tools): cross-reference search and browse tools when both are on
• feat(core): enable KVS model-list compression writer (phase 2)
• feat(macos): configurable Quick Prompt shortcut and App Visibility settings
• feat(ui): apply brand backdrop across chat, Settings, and onboarding
• feat(chat): International Orange backdrop and clearer message bubbles
• feat(folders): unify move-folder menus with icons and tinted glyphs
• fix(macos-chat): pin transcript to bottom on send in long convos
• fix(settings): stop model picker and "Updated " from emptying
• fix(local-tools): make OpenAI Responses follow-up work on OpenRouter
• fix(chat): unwrap OpenRouter error.metadata in chat banners
• fix(chat): surface gateway API errors in banners
• fix(chat): also silence SwiftLint redundant_discardable_let
• fix(chat): keep pending-queue subscribe line SwiftFormat-safe
• fix(chat): restore ViewBuilder builds for pending queue subscription
• fix(chat): subscribe pending-message bar to queue change counter
• fix(core): stop stale sheet onDismiss cancelling chained local tools
• fix(ios): pause streaming auto-scroll during user touch/deceleration
• fix(ios): tighten toolbar spacing between org chip and new chat
• fix(macos): align chat toolbar chrome with primary styling
• fix(ui): align iOS chat toolbar organize chip and menus
• refactor(chat): split StandardMessageContentView into support file
• refactor(core): split Responses DTOs and test helpers across files
• refactor(macos-chat): relocate folder chip beside New Chat toolbar cluster

• feat(core): conversation folders, grouping, and organize flows
• fix(chat): unbreak OpenAI image-edit follow-ups in /responses
• fix(core): raise local tool hop limit from 5 to 25
• fix(chat): resolve huge-code-block crash via Textual TextBuilder fix
• fix(chat): restore VoiceOver body for expanded message rows
• fix(chat): macOS empty-state inset + Ready to Chat body typography
• fix(macos): replace hero Image Button with tap gesture layout

• feat(sidebar): collapsible conversation sections with synced persistence
• fix(macos): re-anchor LazyVStack transcript after mount race
• fix(chat): persist built-in provider before model picker resolves
• fix(chat): seed message cache and stabilize macOS transcript layout
• fix(settings): tolerate transient iCloud Keychain misses
• fix(macos): make error observation archive-safe
• fix(macos): bound long chat errors in bottom controls
• fix(settings): keep model refresh freshness device-local
• fix(ios): improve chat toolbar picker sizing
• fix(streaming): compile render-cost logging in release
• fix(chat): stop streaming dots from bouncing
• fix(chat): keep streaming indicator visible during thinking
• fix(ios): allow chat errors to wrap
• fix(chat): stream indicator in layout, not over Textual
• fix(chat): macOS streaming dots overlay streak
• fix(settings): eliminate the "marketing screen with keys present" regression
• fix(ios): stop transcript bounce during streaming
• fix(ios): restore Liquid Glass toolbar capsules and picker colors
• chore: bump deps.
• perf(streaming): defer LaTeX rendering while streaming
• perf(streaming): adapt UI cadence to render cost
• perf(streaming): restore ~30fps UI throttle; align Quick Prompt

• feat(chat): native transcript lists on iOS and macOS
• feat(images): add streaming partial previews for OpenAI image generation
• feat(images): stream OpenAI image previews
• feat(images): OpenAI image gen on OpenRouter; drop Vercel path
• feat(images): OpenAI image generation via Responses API image_generation tool
• feat(images): Gemini image output via OpenRouter + Vercel gateways
• feat(images): Gemini image output, origin tag, full-width render
• fix(chat): VStack multi-block markdown; iOS transcript cell sizing
• fix(ios): compose UICollectionView insets from measured safeAreaBar heights
• fix(settings): ship compressed model-list reader before writer
• fix(settings): chat readiness gates on key presence, not stale test
• fix(errors): surface hallucinated tool name and special-case hop limit
• fix(local-tools): headless mode uses WebPage API, not URLSession
• fix(endemic-llm): stop referencing disabled local tools to the model
• perf(chat): consolidate streaming auto-follow on revision signal
• perf(chat): trim message accessibility payloads
• perf(chat): cache parsed message content for visible rows
• perf(settings): LZFSE-compress provider model lists in iCloud KVS
• refactor(chat): remove automatic conversation collapse
• refactor(core): remove dead code and align build metadata
• refactor(chat): remove "long press any message to edit" helper tip

• feat(core): Chat Completions local tool loop for Z.AI and gateways
• feat(core): stream Gemini tool calls end-to-end via local tool loop
• feat(core): stream Anthropic tool calls end-to-end via local tool loop
• feat(settings): split Local Browser Use into Search + Browse toggles
• feat(core): in-modal recovery for local search
• feat(core): stream OpenAI post-tool continuations end-to-end + parallel tool calls
• style(settings): make macOS section headers dominant

• fix(core): non-thinking responses fail on Anthropic Opus 4.7+ due to explicit temperature
• fix(core): heal streaming-thinking tables broken by mid-row blank lines
• fix(core): restore macOS chat hit-testing after sidebar collapse

• feat(chat): searchable model picker for large lists
• fix(chat): match searchable model picker to Menu styling
• fix(chat): Textual markdown chunking and truncation mask only when fading
• fix(chat): cap last-message auto-expand to avoid markdown stack blowups
• fix(ios): prevent content scrolling during sidebar edge swipe
• fix(ui): remove Beta chip from AI Reasoning in advanced modal
• fix(core): review prompt uses host app product name
• fix(core): harden chat sync, URLs, and title generation for crash mitigation
• fix: add remote-notification background mode for CloudKit sync
• fix(core): per-message expand stuck after Collapse All
• fix(core): stream thinking UI before think close tag
• chore: track Xcode workspace Package.resolved in git
• perf(a11y): scale preview icons with @ScaledMetric
• perf(core): replace release prints with os.Logger via AppLog
• refactor(core): extract large files into focused modules
• refactor(core): replace ScrollViewReader with ScrollPosition in sidebar
• refactor(core): migrate settings and helpers to @observable
• refactor(core): remove LegacyChatMessage alias and getWebSearchTools
• refactor(core): remove dead DrawerView struct and clean up tests

• feat(message): always show full content for last message, no Show more
• feat(message): add header actions menu button for message actions
• fix(chat): replace position-based auto-scroll break with gesture detection
• fix(markdown): close unclosed code fences from truncated responses
• fix(message): rename Copy to Copy Message in context menu
• perf(chat): auto-collapse older messages on new message submission
• perf(streaming): reduce observation cascades during streaming

fix: bug fixes and improvements

• fix(build): pin Textual to patched revision for iOS archive
• refactor(ui): consolidate beta chips, simplify Ollama settings copy
• refactor(markdown): migrate MarkdownUI to Textual, keep LaTeXSwiftUI for math, remove code block copy

• feat(reasoning): always display thinking when returned, regardless of toggle
• feat(reasoning): support reasoning option for all providers including custom OpenAI
• feat(vercel): add reasoning/thinking support for Vercel AI Gateway
• fix(providers): send reasoning_effort none for custom OpenAI-compatible title generation
• fix(settings): preserve model selection per custom OpenAI provider
• fix(zai): send explicit thinking.type disabled when toggle off
• fix(custom-provider): parse native Ollama token counts and remove token estimation fallback

• feat(settings): double system message character limit to 10k
• fix(ios): preserve show-more position while keeping initial bottom placement
• fix(scroll): restore scroll-to-bottom, auto-follow, and geometry-based break detection (iOS and macOS)

• feat(quickprompt): render markdown continuously during streaming
• feat(shortcuts): save conversations to history
• feat(ios): swipe from left edge to open drawer
• fix(ios): prevent scroll jump when expanding last message at bottom
• fix(links): support ticket and markdown links open correctly on macOS and iOS

• feat(widget): add iOS lock screen widget
• feat(settings): option to auto-delete conversations after X days
• feat(ui): remove bubble view, standardize on document layout
• fix(sidebar): fix conversation group ordering and add comprehensive tests

refactor(ToS): centralize receipt store, global ToS agreement

• feat(macos): add View menu zoom in/out for macOS
• feat(local-browser-tools): Phase 1 local browser tool use for OpenAI direct
• feat(local-browser): hardcode extraction limit, inline links, parser extraction, settings copy
• feat(local-browser): improve tool transcript visibility, extraction, and OS gating
• feat(settings): refine local browser tools + server-side web search UX
• feat(gemini): add thinking/reasoning support for Google AI Studio
• feat(ui): hide reasoning section for unsupported providers
• feat(zai): add thinking support
• feat(anthropic): use adaptive thinking for all 4.6+ variants
• feat(anthropic): add extended thinking support
• feat(widget): implement AI Digest widget extension
• feat(widget): AI Digest Widget WIP implementation
• revert(widget): back out AI Digest Widget implementation... too frustrating to get working
• feat(sidebar): add Duplicate to conversation context menu
• fix(openai): support dual-tool selection and valid web_search encoding
• fix(settings): persist provider selection when switching to previously-used provider
• fix(ios): display zoom on iPhone SE 2022 truncates text and UI elements
• perf(test): remove mock streaming delay and reduce ensemble concurrency delay
• perf(test): speed up test suite from ~15s to ~7s
• refactor(settings): normalize typography, alignment, and spacing across macOS and iOS
• style(settings): use SettingsSectionHeader for Model Filters in iOS

• feat(custom-provider): add OpenAI-compatible custom provider support
• feat(custom-params): prepend messages for Chat Completions system prompts
• feat(settings): add Beta chip to OpenAI-Compatible Providers section
• feat(settings): OpenAI-Compatible section intro, Add Provider UX, a11y
• feat(custom-provider): immediately fetch models when adding custom provider
• feat(custom-provider): enable attachments for OpenAI-compatible providers
• feat(custom-provider): add title model picker below API key row
• feat: disable AI Reasoning for unsupported providers; improve custom provider modal UI
• feat(custom-provider): harden API key requirements and fix ensemble metadata
• fix(openrouter): use provider-appropriate reasoning-off for Anthropic models
• fix(settings): improve macOS settings sizing and simplify status messages
• fix(latex): add horizontal scroll for wide block equations
• fix(settings): align macOS add-button styling across API key sections
• fix(custom-provider): OpenRouter compatibility, title picker UX, prune debug logs
• fix(custom-provider): apply model inclusion/exclusion filters to custom provider models
• fix(openrouter): explicitly disable reasoning when off
• perf(ensemble): parallelize Face/Off candidate calls with async let
• refactor(models): replace smart model selection with hardcoded defaults
• refactor: DRY pass across settings, URLs, and attachment views
• refactor: deduplicate SettingsManager init and title generation dispatch
• refactor(core): remove verified dead code paths

• feat(search): add "Only Search When Requested" smart search toggle
• feat(attachments): add interactive preview and PDF thumbnails
• feat(chat): image paste support for iOS and macOS
• feat(chat): hide provider picker when only one provider is configured
• feat(model-filters): add positive model inclusion filters alongside existing exclusion filters
• fix(openrouter): add PDF file attachment support to chat completions

• feat(openai): add reasoning/thinking support with collapsible UI
• feat(openrouter): add OpenAI-style reasoning support for streaming chat
• feat(settings): improve provider recommendations and web search warnings
• feat(settings): split API keys into Direct/Multi-providers, improve ZDR copy and UX
• fix(ui): restore link colors in markdown and unify with Link views
• fix(quick-prompt): persist thinking and raw API response
• fix(reasoning): gate capture by request config and prevent double-send race
• fix(streaming): preserve thinking content after streaming completes
• fix(streaming): repair chunk normalizer corruption and Face/Off judgment reliability
• fix(openrouter): add web search plugin support
• fix(openai): remove unnecessary reasoning param from title generation
• fix(markdown): stop chunking from splitting fenced code blocks
• chore: remove dead code (unused CoreData imports, empty deinit)
• docs(quick-prompt): document Face/Off intentionally not used
• docs(settings): clarify OpenRouter recommendation copy and link ZDR once
• style(settings): reduce API key toggle size on macOS

• feat(shortcuts): add Siri and Shortcuts integration
• feat(vercel): add app attribution headers for Vercel AI Gateway
• feat(vercel): add Zero Data Retention toggle for Vercel AI Gateway
• fix(shortcuts): add Siri entitlement, fix phrase collision, add ping test
• refactor(settings): improve API key addition flow
• style(settings): remove redundant Provider row from Add API Key views
• style(onboarding): further copy refinements
• style(onboarding): tighten welcome screen copy and layout

• feat(settings): add model exclusion filters for large provider lists
• feat: add Vercel AI Gateway as new API provider
• fix: improve title generation prompt for shorter titles
• fix(macos): fix Cmd-F Find in conversation
• refactor(settings): rename Test to Update in API keys UI

• feat(a11y): add Voice Control, Differentiate Without Color, Larger Text, and Sufficient Contrast support
• fix(macos): restore arrow key navigation in sidebar
• fix(markdown): restore inter-block spacing in chunked content
• fix(streaming): show error banner for in-stream API failures
• fix(scroll): reduce excessive bottom spacer during auto-scroll
• refactor: DRY up duplicated view code in three files
• refactor: remove unused code identified by Periphery and manual review

• perf(messages): string-truncate long messages to reduce CPU usage
• perf(scroll): VStack + scroll-to-bottom + 5fps throttle for reliable positioning
• perf(streaming): fix high CPU during streaming with @observable and scroll throttling
• perf(views): fix iOS watchdog crash by removing message view observation overhead
• refactor(messages): revert to VStack
• refactor(scroll): migrate to modern ScrollPosition API with auto-follow

• feat(chat): add collapse/expand for messages in document view
• fix(a11y): improve accessibility for collapse/expand feature
• fix(a11y): add accessibility labels to ErrorBannerView
• fix(anthropic): discard pre-tool text to fix "double answer" with web search
• fix(anthropic): handle unsupported client-side tool requests gracefully
• fix(ios): show auto-scroll button on first AI response
• chore: auto-applied settings.
• perf(chat): improve CPU usage and fix scroll issues on macOS
• docs: add critical performance warnings for LazyVStack

• feat(a11y): expose markdown headings to VoiceOver rotor navigation
• fix: resolve streaming buffer issues affecting UI and content preservation
• fix: render markdown headers in pure-markdown paragraphs
• fix: preserve user message and partial AI response on streaming error
• perf: use in-memory buffer for streaming to eliminate sidebar re-evaluation
• perf: reduce redundant LaTeX parsing in MarkdownTextView
• perf: throttle UI updates during streaming with VoiceOver bypass
• perf: throttle SwiftData saves during streaming to reduce CPU/energy usage
• refactor: DRY up duplicated code across providers and views

• feat(a11y): complete accessibility assessment with P3 resolution
• feat(a11y): implement P2 accessibility features
• feat(a11y): implement P0 and P1 accessibility features
• fix(ios): position cursor snug against bottom gutter in chat input
• fix(ios): enable keyboard avoidance in expanded input sheet
• fix(ios): prevent text overlap with buttons in expanded chat input
• fix(macos): reduce excessive side margins in chat input
• fix(messages): prevent crash when accessing deleted SwiftData models
• fix(quick-prompt): Open in App button not working on macOS
• perf(launch): improve macOS app startup time and window activation
• chore: linting.

• feat(openrouter): add OpenRouter provider integration
• feat: add OpenRouter to marketing screens and sort providers alphabetically
• feat(settings): add OpenRouter to Custom API Parameters examples
• fix(ui): align iOS pending messages box with macOS rectangular styling
• test: modernize and optimize test suite
• test: modernize and DRY test suite
• chore: complete feature and bump version.
• chore: update OpenRouter HTTP-Referer to folding-sky.com/cumbersome
• docs(plans): add OpenRouter integration plan

• feat(chat): enable concurrent chats with per-conversation state
• feat(chat): add pending message queue system
• feat(chat): preserve streaming content when user stops response
• fix(streaming): add cancellation checks in provider streaming loops
• fix(ios): clear message text after sending
• fix(views): restore erroneously removed code from Periphery scan
• fix(chat): prevent sidebar thrashing during concurrent streaming
• chore: bump to 1.22.0
• refactor(settings): split SettingsViewModel into focused files
• refactor(viewmodel): extract ChatViewModel into focused helpers
• docs: add pending message queue to feature highlights
• docs: add concurrent chats to feature highlights

• feat(zai): Add Z.ai provider support
• feat(attachments): add macOS drag-and-drop file support
• feat(attachments): enable multi-selection for image and file pickers
• fix(views): remove per-item copy buttons from JSONTreeView
• fix(latex): prevent false positives on currency ranges and prose content
• fix(markdown): reduce chunk size to 4000 chars for safer margin
• fix(markdown): prevent stack overflow when rendering large text
• chore: reduce image sizes using imageoptim.
• docs: document xAI abandonment, pivot to Z.ai support

• feat(latex): LaTeX content parsing and rendering
• feat(copy): add Copy Conversation feature with context menu
• feat(export): add conversation JSON export from sidebar context menu
• refactor: remove dead legacy code, rename LegacyChatMessage to APIMessage
• docs(plans): add conversation JSON export feature plan
• docs: add SwiftUI-only policy to project rules

• feat(deeplink): add conversation deep links with Copy Deep Link menu option
• feat(ui): add copy button to markdown code blocks
• chore: bump dependencies

• feat(icons): add Joystick alternate icon and improve Settings UI
• feat(icons): add Gear Mesh alternate icon and fix macOS Dock sizing
• feat(settings): Redesign iOS Settings with card-based layout
• feat(settings): add alternate app icons and switcher UI
• feat(assets): add alternative 'Cu' periodic table style app icons
• feat(macos): toggle menu bar icon visibility
• fix(lint): move unused_declaration to analyzer_rules section
• fix(settings): separate icon choices, fix assets, align UI, use local storage
• fix(attachments): enforce API-safe image bytes for Anthropic
• fix: dedupe authenticated request building
• test: remove useless, redundant, and brittle tests
• refactor(views): extract components from large view files
• refactor: remove unused code identified by Periphery
• refactor(tooling): configure Periphery to be more strict
• refactor(views): remove unused @State properties from ChatInterfaceView
• refactor(views): extract ChatInterfaceView from MainNavigationView
• refactor(views): extract components from MacOSNavigationView.swift
• docs(plans): document local storage decision for icon preference

• feat: auto-shrink images to 4mb to account for strict Anthropic image size limits.
• feat: long-click on any user message to restart convo from that point, allowing for renewing conversation history by restarting the chat at any prior user message in a convo.
• feat: long-press chat Send button provides context menu to send to new chat vs the existing one.
• fix: a bug prevented icloud sync of chats with images/pdfs/files across devices. this fixes. IMPORTANT: delete old convos that have images/files for sync to work again.

• feat: enable pinned conversations from drawer/sidebar.
• chore: rename plans to .ai-plans.
• docs: plan pin convo feature.

• feat: quick prompt (press Option + Space in macOS for super-fast prompting).
• feat: PDF and other attachment analysis and syncing between devices.
• fix: macOS specific copy.
• test: support PDF and other attachment analysis.
• chore: bump to 1.15.0.
• docs: help if processing.
• docs: closing out quick prompt feature.
• docs: key insights on missing CloudKit production promotion.

• feat: ability to view raw API response.
• feat: enable iOS background tasks to allow completion of in-progress chats while in another app.
• fix: various improvements to raw API view.
• fix: DRY meta information in face/off responses; fix edited face/off.
• fix: change sidebar selected to branded orange with white text.
• fix: sidebar button colors.
• test: updated ensemble mode.
• test: add for sidebar, and update rules.
• chore: complete raw API viewer feature.
• chore: bump to 1.13.0.
• chore: rename docs to done.md.
• refactor: more logging for gemini calls.
• docs: raw API response plan.
• docs: mark background feature done.
• docs: plan iOS background streaming.
• docs: update README.

• feat: search feature.
• feat: sidebar liquid glass.
• feat: new icons for iOS and macOS.
• fix: macOS sidebar button text in small width view.
• fix: button colors in non-liquid glass iOS.
• fix: iOS drawer fade-out extends above Search.
• fix: auto-increment build count.
• fix: iOS search input focus and soft keyboard.
• fix: fade in bottom of drawer.
• fix: make release ordering of edit types.
• fix: remove Sora as an OpenAI option.
• fix: Settings color when selected.
• fix: test improvement.
• fix: Unknown provider in intro iOS copy; missing macOS copy entirely.
• chore: update to reco settings and bump version.
• chore: bump to 1.12.0.

• fix: soft cursor never vanishing in iOS.
• fix: iOS PhotosPicker selection state.
• fix: OpenAI follow-up message error to original message with attachment.
• chore: bump to 1.10.1.
• chore: reco entitlement fix.
• docs: for soft keyboard issue.

Attach images and files to prompts in iOS, iPadOS, and macOS.

• TUNE ALL API PARAMS: Power users can now send custom parameters directly to AI provider APIs. Access advanced features like reasoning effort controls, sampling parameters, and custom stop sequences without waiting for app updates.
• Configure parameters in Advanced Features modal (tap + button in chat)
• Works across OpenAI, Anthropic, and Gemini
• Override built-in settings when needed
• Syncs via iCloud across all your devices
• Other Improvements:
• Enhanced chat input layout with improved button placement
• Platform-specific UI refinements for iOS and macOS
• Better handling of complex API configurations

• migrate to SwiftData for better cross-device syncing.
• overscroll UI improvements.
• more Liquid Glass for iOS and macOS 26.
• ### Bug Fixes
• scrolling spacing.
• deleting messages issue.
• streaming messages and swiftdata and cloudkit.
• face/off mode and migration.
• for smaller screens like 16e.
• indicate thinking + tools for all out tokens.
• glass style on ios >= 26.
• refine face/off button size in iOS.
• add more padding to input.
• auto-scroll.
• shorter input text.
• buttons inside macos chat input.
• ### Maintenance
• bump version to 1.8.0 build 27
• enable code stripping.
• bump to 1.8.0.
• try to fix legacy data.
• uninstall dev script.
• ### Tests
• swiftdata and cloudkit.
• complete swiftdata.
• keep refining.
• get them compiling.
• ### Documentation
• mostly complete swiftdata.
• plan swiftdata migration.
• add refactoring doc.
• liquid glass rules.
• ### Refactoring
• MainNavigationView.

• organize convos by date.
• improve macOS title area.
• remove needless Your Chats and refresh in macOS and iOS.
• ### Bug Fixes
• adjust token counts.
• remove logos from sidebars.

• feat: auto-scroll to bottom when going to old convo.
• feat: reorder convo list based on last update.
• fix: subtle issue with iOS auto-scrolling.
• ci: fix changelog auto-generation.

Fix bug that was preventing full chat from being sent to OpenAI.

• Gemini / Google AI Studio API key support now available.
• Auto-generate titles using low-cost AI now available and ON by default.
• ### Bug Fixes
• no extra spacing needed for OpenAI and Gemini.
• duplicated pre-search content in Gemini.
• bug related to re-using old title when trying to swap to old chat during in progress new chat.
• don't overly restrict auto-title length.
• title summary issue with OpenAI.
• iCloud sync issue across devices.
• errant spaces in AI responses.
• swap provider and model mid-convo based on drop-down changes.
• ### Maintenance
• update CHANGELOG for v1.5.0-build19
• bump version to 1.5.0 build 19
• update marketing copy.
• bump and DRY.
• tests and debugging refinements for auto-generate titles feat.
• adjust cursor rules.
• ### CI/CD
• bump to 1.5.0.
• remedy issue with release.
• ### Documentation
• duplicated pre-search content in Gemini.
• ### Tests
• new Gemini option.

• ### Features
• auto-scroll option.
• add new chat icon in upper-right in macOS.
• ### Bug Fixes
• restore non-streaming OpenAI calls.
• remove PRODUCT_PACKAGE_TYPE.
• reduce scrolling into infinity whitespace.
• MacOS double carets in drop-downs.
• improve auto-release notes.
• ### Build System
• try to fix app store connect distro issue.
• refine UI tests.
• prep release 1.4.0
• test and DRY for scrolling refinements.
• Modernize to iOS 18/macOS 15 with replace ScrollViewReader with .scrollPosition.
• Modernize to iOS 18/macOS 15 with macOS Window Management.
• Modernize to iOS 18/macOS 15 with Swift 6 Typed Throws.
• Replace NotificationCenter with Swift Observation.
• Modernize to iOS 18/macOS 15 with SF Symbols 6 with Animations.
• Modernize to iOS 18/macOS 15 with Swift 6 strict concurrency.

• Agent tool (search) option now available.
• Various bug fixes and improvements.

Bump dependencies. Fix soft keyboard issue, allowing returns within prompts for better iOS editing.

• FACE/OFF MODE IS HERE
• Generate 3 AI responses with different creativity levels (conservative, balanced, creative). Then an AI judge evaluates all 3, picks the winner, and tells you why it's superior.
• Stop doing manual trial-and-error. Get the best response on the first try.
• Perfect for critical tasks: business emails, complex code, research. When quality matters more than cost, Face/Off Mode delivers.
• Why consumer apps will never build this: Subscription models want you messaging more, not getting perfect answers immediately. With pay-per-use, our incentives align with yours.
• Uses ~5x the tokens, but when you need the absolute best response, it's worth it.

• DOCUMENT WORKSPACE
• Finally. Stop squinting at chat bubbles. Full-screen document interface for actual work. Edit AI responses inline. Read long outputs without wanting to throw your phone.
• ICLOUD SYNC
• Your conversations, API keys, and settings now sync across iPhone, iPad, and Mac via your personal iCloud. Not our servers-yours. Start a conversation on your phone, finish it on your Mac.
• BETTER CONVERSATION EDITING
• Edit any message-yours or the AI's-to refine context. Delete off-topic tangents. Fix the AI's mistakes mid-conversation. Better context = better responses.
• And of course a bunch of bug fixes and little-bitty features.

Initial release.