- Scan regions can be disabled (Del/Backspace) instead of deleted, shown greyed out
- Resize scan regions by dragging timeline edges or editing table cells
- Grey ghost overlay shows trimmed portions of resized regions
- Ctrl+Z undo for disable, resize, drag, and negative toggle actions
- Fix training stats including scan-exported clips when checkbox unchecked
- Switch classifier to HistGradientBoostingClassifier (multi-threaded)
- Timestamped model saves with latest copy at base path
- Fix next-folder counter not detecting scan export folders
- Each scan area exports to its own numbered clip folder
- Platform-aware HW encoder detection (Linux/Windows/macOS)
- Auto-detect VAAPI render device instead of hardcoding
- Use shutil.move for cross-drive safety on Windows
- Comprehensive README rewrite with scan workflow documentation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fuse overlapping scan regions before display (merge adjacent 1s-hop windows)
- Hard negatives: mark false positives from scan panel for training feedback
- Toggle with "Add to Negatives" button, red text + red timeline regions
- Stored in dedicated hard_negatives table, always included in training
- Model versioning: auto-backup on retrain, right-click model combo to rollback
- Scan review mode: "Review" toggle hides spread/markers for free navigation
- Scan exports: saved to DB with scan_export flag, no timeline markers
- Training dialog checkbox to optionally include scan exports
- Single group folder per batch with area numbering (clip_042_a1_0.mp4)
- Export scan results: skip negatives, skip regions < 8s, respect spread
- Button shows estimated clip count, updates on spread/fuse/negative changes
- Timeline: reload scan regions on file load, "Clear all markers" context menu
- Default training model changed to HUBERT_XLARGE
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Stash profile and crop_center at export start for async safety
- Scope get_group/delete_group by profile to prevent cross-profile leaks
- Guard auto-negative sampling when no markers exist (prevents flood)
- Wrap ffmpeg subprocess with clean timeout error message
- Fix scan-all panel reload to use stashed profile, not live value
- Remove dead warnings import
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace librosa with direct ffmpeg subprocess for 10x faster audio loading
- Add ScanResultsPanel with per-model tabs, seek-on-click, delete, and export
- Persist scan results in DB per (filename, profile, model)
- Add model selector dropdown to switch between trained embedding models
- Add "Scan All" button for batch scanning playlist videos
- Support manual negative examples via negative class folder
- Configurable auto-negative margin (default 30s, 0 = disabled)
- Deduplicate nearby training markers (8s min gap)
- Parallel audio loading with ThreadPoolExecutor during training
- Progress callbacks from training for UI status updates
- Cache bypass in scan_video (skip audio loading when embeddings cached)
- Move all caches (models, embeddings, downloads) into project directory
- Add 8cut.sh launcher script with auto venv/conda detection
- Fix 11 bugs across thread safety, signal handling, and state management
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix test_utils.py importing build_annotation_json_path from main
instead of core.annotations (all 59 tests pass now)
- Fix get_training_data double-counting clips at same start_time
in both positive and soft sets — subtract positive from soft
- Add cancel_flag to train_classifier so training can be interrupted
between videos (TrainWorker passes self as cancel_flag)
- Remove orphaned core/export.py (was for deleted server API)
- Remove stale Dockerfile and docker-compose.yml (referenced server)
- Clean up leftover server/__pycache__ and client/ build artifacts
- Add torch to requirements.txt (was only mentioned in comments)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove legacy distance-mode scanning (build_profile, _similarity, etc.)
and hand-crafted intensity features — pipeline is now embedding-only
- Integrate Microsoft BEATs as embedding option alongside wav2vec2/HuBERT
- Add TrainDialog with positive class selector, model picker, video dir
fallback, and live training stats
- Add TrainWorker QThread with cancel support and proper lifecycle cleanup
- Add source_path column to DB for robust source video tracking
- Add get_export_folders/get_training_data/get_training_stats to DB
- Wire source_path in all export DB writes (_on_clip_done, _on_auto_clip_done)
- Cancel scan/train workers in closeEvent to prevent use-after-free crashes
- Add setup_env.sh supporting both conda and python venv (CUDA 12.8)
- Update requirements.txt with all actual dependencies
- Update 8cut_train.py with --positive flag for new DB-driven training
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause of poor discrimination: MFCC[0] (energy) dominated the
feature vector, making cosine similarity see all audio as similar.
Changes:
- Skip MFCC[0], use 12 coefficients instead of 20
- Add delta MFCCs for temporal dynamics
- Add 7-band spectral contrast for tonal vs noise quality
- Switch from cosine similarity to euclidean-distance-based score
- Pre-compute STFT once for whole file (10-20x faster)
- Vectorized sliding window via cumulative sums (no Python loop)
- Lower sample rate 22050→16000 Hz (faster, no quality loss)
- 62-dim feature vector (was 40-dim mean+std of raw MFCCs)
- Default threshold 0.05 (new similarity scale)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. Rename ScanWorker.finished → scan_done to stop shadowing
QThread.finished. Previously, cancelled scans leaked the QThread
because the custom signal was never emitted.
2. Block signals on combobox reset in _on_scan_ref_changed to
prevent re-entrant call when user cancels folder dialog.
3. Merge overlapping scan regions into clusters before S-key
navigation so it jumps to the next distinct match, not 1s forward
through overlapping windows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When cancelling a scan during file change, connect finished signal
to deleteLater instead of calling it immediately on a running thread.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Scan button, threshold spinner, mode combobox, and reference source
combobox to the settings row. Implement handler methods for starting scans,
handling results/errors, cleanup of workers, and reference folder selection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add scan region storage and rendering to TimelineWidget:
- _scan_regions list in __init__ for (start, end, score) tuples
- set_scan_regions() and clear_scan_regions() methods
- paintEvent draws semi-transparent blue rectangles with score-based opacity
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Switch DELETE /export to query param (path param strips leading /)
- Add CropKeyframe Pydantic model for typed keyframe validation
- Convert keyframes to tuples before passing to apply_keyframes_to_jobs
- Remove dead QFrame import from main.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Autoclip (A): adjusts clip count to fit current pause position
- Pause no longer resets playback position — stays where paused
- Play resumes from pause point instead of restarting
- Spread/clips changes update loop end without restarting playback
- Number keys 1-9 export to subprofiles
- Click-away clears focus from spinboxes so hotkeys work again
- Lock mode: double-click marker jumps cursor to end of clip span
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Subprofiles: lightweight export variants that append a suffix to the
export folder (e.g. _soft, _intense). Each gets its own export button
in the transport row. Managed via "+" menu, persisted in QSettings.
- Play loop now updates immediately when spread/clips spinboxes change.
- Lock mode: ignore stale mpv position updates while user is dragging
to prevent the play position from jumping back.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- setup-windows.ps1: downloads libmpv DLL and ffmpeg, installs pip deps
- 8cut.bat: double-click launcher
- main.py: add_dll_directory for libmpv next to script (not just frozen)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enables cross-platform builds for Windows and macOS. Adds _bin() helper
to resolve bundled ffmpeg in frozen builds, and configures ctypes library
path for bundled libmpv.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the bottom status bar with a right-aligned label on the
settings row, saving vertical space. Add "Export complete" message
when a batch finishes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a pure function that returns the latest keyframe at or before a
given time (with tolerance), replacing the inline lookup pattern that
appears multiple times in main.py. Includes 6 tests covering empty
list, before-first, exact match, between, after-last, and tolerance.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extended selection mode (Ctrl+click, Shift+click) enabled. Right-click
context menu adapts to selection count — hide or remove multiple files
at once. Single click without modifiers still loads the file.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instead of hiding QListWidget items (which causes Qt to miscalculate
scroll position), the playlist now rebuilds its contents from scratch
whenever visibility changes. Only visible items exist in the widget.
- _rebuild() clears and repopulates from _paths filtered by visibility
- mark_done/unmark_done update in-place for visible items
- set_hidden_basenames and set_hide_exported trigger _rebuild
- Removes _LockedScrollBar, all scroll hacks, and workarounds
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
_LockedScrollBar subclasses QScrollBar and blocks setValue when locked.
This catches ALL scroll sources — Qt layout, auto-scroll, item changes —
not just scrollTo. Locked during setCurrentRow, visibility changes,
playlist checks, and video load (200ms after load to catch late events).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Keyframes were skipped when ratio was None (random mode), and random
crop was overwriting the resolved center with base_center. Now
keyframes resolve the center for all jobs first, then random crop
assigns the ratio while preserving the per-job center.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ExportWorker now uses Popen instead of subprocess.run so running
ffmpeg processes can be killed on cancel. Cancel button appears
between Export and worker count spinner, enabled during export.
Clips already finished before cancel are kept in the DB.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace timer hacks and scrollbar save/restore with a proper fix:
PlaylistWidget.scrollTo() is overridden to no-op when _scroll_locked
is set. Lock is held during setCurrentRow, visibility changes,
playlist checks, and video load — all operations where Qt's internal
auto-scroll was causing the list to jump.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
mpv video surface resize triggers layout events across multiple event
loop cycles. A single deferred restore was too early.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Qt processes layout changes asynchronously, so restoring the scrollbar
immediately after _after_load was too early. Use QTimer.singleShot(0)
to restore after Qt finishes processing pending layout events.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Video load triggers layout changes (buttons, crop bar, preview window)
that cause Qt to recalculate the playlist scrollbar position. Now saves
the scroll value in _load_file and restores it at the end of _after_load.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>