fix: bug audit — broken test imports, training data overlap, cleanup

- 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>

requirements.txt

@@ -9,8 +9,9 @@ scikit-learn>=1.3
 joblib>=1.3
 soundfile>=0.12
 
-# Deep learning (torch installed separately for CUDA support)
-# torch and torchaudio are installed via --index-url in setup_env.sh
+# Deep learning — install via setup_env.sh for correct CUDA version,
+# or manually: pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu128
+torch>=2.0
 torchaudio>=2.0
 
 # Object detection