Version History

This update introduces critical security enhancements, major performance optimizations for document management, and full compatibility with the latest reasoning models.

Performance & UI Optimizations

• Instant Document Deletion: Upgraded vector deletion logic to use batching. Removing documents from your index is now up to 10x faster.
• Optimistic UI Updates: Deletion of indexes and namespaces now updates instantly in the UI for a much snappier experience.
• Namespace Management: Added a new Namespace deletion option directly in the Documents tab so you can wipe custom namespaces cleanly.
• Background Syncing: Index lists now sync seamlessly in the background across views.

Security & Architecture

• Secure API Key Storage: API keys are now stored exclusively in the system Keychain via a secure settings store, replacing process environment variables.
• UserDefaults Hardening: Wiped legacy plain-text API credentials from unencrypted UserDefaults storage.
• Reasoning Model Support: Updated API parameters to fully align with latest OpenAI models, including native reasoning effort configuration and completion token limits.

Stability & Bug Fixes

• Migrated navigation toolbars to cross-platform SwiftUI layouts to improve UI stability.
• Resolved background streaming task retention warnings.
• Expanded unit test coverage across all core services for improved reliability.

Version 2.2 brings GPT-5.2 support, smart prompts, and bunch of other stuff. I reworked the UI entirely..

GPT-5.2 REASONING MODEL

• Full GPT-5.2 support with 400K context and 128K output tokens
• New reasoning effort levels: Off, Low, Med, High, and Max (xhigh)
• Updated token limits for modern AI capabilities

SMART EXAMPLE PROMPTS

• Contextual prompts based on your selected index and namespace
• Four categories: Discover, Analyze, Extract, Compare
• Tap any suggestion to instantly search
• Prompts adapt when Charts & Calculations is enabled

CHARTS & CALCULATIONS (Code Interpreter)

• Visualize data from your documents as charts
• Calculate totals, averages, and trends
• Extract structured tables and export to CSV/JSON
• Create timelines and comparison visualizations
• Quick Settings panel with sliders and presets
• Haptic feedback and custom system prompts

Version 2.0 brings foundational improvements to answer generation, reliability, and user control.

OPENAI RESPONSES API & GPT-5

• Migrated from Chat Completions to structured Responses API
• Native GPT-5 reasoning model with dynamic effort controls
• Existing models (GPT-4o, GPT-4o mini) continue with temperature/top-p
• Settings UI conditionally renders correct parameters
• Structured "input" field with system/user content arrays

SERVER-SENT EVENTS STREAMING

• Answers stream token-by-token instead of blocking
• Typing indicator appears immediately while waiting
• Stop button cancels mid-generation with clear feedback
• Watchdog timer detects stalls and triggers fallback completion

CONVERSATION MEMORY

• Bounded client mode includes last ~8 messages for context
• Server-managed threads use OpenAI conversation IDs
• Toggle between modes in Settings for privacy preferences
• Follow-ups understand prior exchanges without restating

RESILIENCE & CIRCUIT BREAKER

• Pinecone health checks run before queries with short timeout
• Circuit breaker prevents calls to unhealthy hosts
• Per-search trace IDs tie logs to specific queries
• Error banners auto-dismiss with user-friendly summaries

PRIVACY & RESET FLOWS

• Settings > Data & Privacy exposes credential reset
• Clears Keychain, conversation history, bookmark consent
• Onboarding messaging clarifies missing keys
• Preflight script blocks accidental credential leaks

CITATION STABILITY & POLISH

• Citations enumerate by offset—no duplicate ID warnings
• Logs tab filters with color-coded levels
• Index host transitions emit structured logs
• Improved keyboard handling and haptic feedback

Behind the scenes: upgraded to OpenAI Responses API, added conditional model parameterization, implemented SSE parsing with cancellation, and wired bounded conversation memory. All changes maintain backward compatibility with existing documents and Pinecone indexes.