New in FencingLab 3.0 1. AI Daily Training Plans - Every day, the AI builds a personalized training target based on your recent video analyses. - Two parts: - Fencing drills — e.g. footwork ladders, bladework exercises, each with a description and duration/reps. - Physical conditioning — e.g. jump rope, push-ups, agility work. - The next day, the AI reviews your latest video to mark the previous target as met / partial / missed, and adapts the new plan from your actual progress. 2. Resumable Video Uploads - Videos now get a stable, content-derived ID, so if an upload fails or is interrupted, retrying continues the same upload instead of starting over or creating a duplicate. - Larger, more reliable uploads via chunked transfer. 3. One-Tap Video Import - Share a video straight into FencingLab from Photos, Files, or any app using the iOS share sheet. - Pick the title, session type (training/competition/drill), and visibility before uploading. 4. Improved AI Analysis - Technical breakdown with coaching moments (screenshot thumbnails of key actions) and an interactive timeline so you can jump straight to the moment that needs work.

Fixes for things that were actively breaking video import/playback: - Session expiry no longer breaks video import. The app now refreshes your login token every time it comes to the foreground, not just on a fresh launch — previously a session left backgrounded past the 7-day token lifetime would silently fail every action (including "Import Video") until you manually logged out and back in. - Uploads survive network blips instead of restarting. A failed chunk (timeout, dropped connection, server hiccup) now resumes from the last successfully-uploaded chunk when you tap Retry, instead of re-sending the whole video from scratch. Bad requests (not just transient errors) still fail cleanly rather than retrying forever. - Fixed the "kicked back to Training Videos" bug. Watching a video (or viewing its details) no longer gets silently interrupted and dumped back to the video list whenever an analysis finishes in the background — traced to a SwiftUI view-identity bug in the tab badge, now fixed. - Video captions no longer cut off mid-sentence. The on-screen caption during playback showed at most 2 lines and truncated with "…"; now it grows to fit the full description. - Coaching moments now show a screenshot of the video frame at that moment (backend already generated these; the UI just wasn't displaying them). - New: scoreboard & touch-indicator detection. The model now explicitly reports whether it can see a physical scoreboard or the touch-indicator light apparatus in the shot (these are real objects in frame, not video overlays, and can drift in/out as the camera moves) — and states plainly when it doesn't see one, instead of silently leaving score fields empty. - New: automatic retry on a bad sample. Same video, same prompt can occasionally produce a degenerate, repetitive response purely from model sampling variance — this is now detected and retried once automatically before being accepted.

FencingLab 2.0 brings a much smoother training workflow: (1) Video up to 5 minutes and Background uploads Long video uploads now continue even if you switch apps or your phone goes to sleep. Upload one clip, start recording the next — no more waiting. (2) Sign in with Google and Apple account One-tap Google Sign-In is now available alongside Apple and email. (3) Guest mode Try the app without creating an account. When you're ready, sign in and your trial credits transfer over. (4) Faster AI analysis Technique, tactics, blade contact, and matchup analyses are faster and more reliable. (5) Smoother video import The "share to FencingLab" flow now picks the current fencer automatically. (6) Numerous bug fixes and performance improvements Thanks for fencing with us — feedback always welcome at support@myphonetools.com.

Based on what was done this session, here's what's new in 1.3.2: Bug Fixes - Fixed landscape video recording — live camera preview was rotated 90° when holding phone sideways - Fixed recording orientation being saved incorrectly for landscape videos - Eliminated the multi-second delay after a 1-minute recording ends before the Cancel/Done buttons appear - Fixed "Failed to load fencer data" error when tapping your name in Profile - Switched Gemini AI model to gemini-3.1-pro-preview for better analysis quality

Version 1.3 Competition Strategy Analyzing a competition bout? FencingLab now generates a dedicated Competition Strategy section — what to do differently in the next point, habits to break immediately, opponent weaknesses to exploit right now, and a closing plan to win or recover. Deeper Tactical Analysis Every analysis now includes distance management assessment, preparation tells (arm extension timing, footwork telegraphing), strip position awareness, and 3 specific tactical adjustments to improve your hit-to-miss ratio. Both your fencer and opponent get a game plan. Better Local AI Results The on-device GPU analysis (Local LLM) now produces structured results matching the quality of cloud analysis — with proper owner/opponent attribution on every detected action. Japanese & Korean Support Analysis and coaching feedback now available in 日本語 and 한국어, in addition to English, Chinese, Spanish, French, and German. Bug Fixes - Fixed analysis mode picker appearing on already-analyzed videos - Fixed server connection issues on physical devices

Version 1.2 Fixed: Public videos no longer show your name when viewing videos uploaded by other users. Improved Restore Purchases — now shows progress while restoring and confirms the result. Auto-closes the subscription screen when a purchase is successfully restored. Better video recording flow — after recording, preview your video before using it. Tap Done to upload or Cancel to re-record.

What's New in This Version Competition Mode Analysis When you mark a video as a Competition session, FencingLab now automatically generates tactical recommendations — specific strategies to exploit your opponent's weaknesses and help you win the next bout. Local AI Support (Free) Analyze your fencing videos using our on-device AI — no credits required and your video never leaves our private servers. Choose between Google Gemini for best quality or Local AI for free private analysis before each video. Bug Fixes & Improvements - Simplified video detail screen for a cleaner experience - Fixed subscription pricing display - Stability and performance improvements