feat(pipelines): compute_harmonization_diagnostics — long-format pre/post ComBat for viz

feat(mri): log run params, metrics, and parquet artifact to MLflow

feat(eeg): log run params, metrics, and parquet artifact to MLflow

feat(bbb): log run params, metrics, and parquet artifact to MLflow

test: cross-pipeline smoke run for all three modalities

fix(mri): handle all-constant features; tighten variance threshold; reorder log

feat(mri): add run_pipeline orchestrator + CLI (NIfTI dir → ComBat Parquet)

fix(mri): pin ComBat transitive deps; clarify np.round(14) intent; guard inputs

feat(mri): add harmonize_combat wrapper around neuroHarmonize.harmonizationLearn

refactor(mri): bind ROI_STATS to callables; guard volume/mask shape mismatch

feat(mri): add extract_features_from_volume (8 ROI octants × 6 stats)

fix(mri): warn on all-False mask; document 6-connectivity erosion caveat

feat(mri): add mask_brain (intensity threshold + morphological opening)

feat(mri): add is_valid_volume guard for NaN/inf/shape/dtype on 3-D arrays

docs(eeg): correct float64 dtype claim; tighten test match; clarify CLI default

feat(eeg): add run_pipeline orchestrator + CLI (FIF/EDF → Parquet)

fix(eeg): NaN-clean features for flat channels; guard zero-size epochs; assert WARNING

fix(eeg): validate epochs after filter to guarantee no NaN in feature table

feat(eeg): flatten 3D epochs into deterministic 2D feat_<ch>_<band|stat> table

refactor(eeg): bind STATS labels to callables; document moment conventions

feat(eeg): add compute_features_from_epoch (PSD bands + 5 statistics)

refactor(eeg): tighten ICA docstring + log accuracy; extract EOG threshold constant

feat(eeg): add remove_artifacts_with_ica with EOG correlation rejection

fix(eeg): guard bandpass_filter against inverted l_freq/h_freq; document picks=all

feat(eeg): add non-mutating bandpass_filter (default 1-40 Hz)

fix(eeg): tighten is_valid_epoch signature; reject non-numeric dtype + -inf

feat(eeg): add is_valid_epoch guard for NaN/inf/shape/dtype

feat(bbb): switch processed output to Parquet for dtype preservation

refactor(bbb): pin LF lineterminator; move DEFAULTs to top; reject dir output

feat(bbb): add run_pipeline orchestrator + CLI entrypoint with idempotent writes

fix(bbb): guard empty input; truncate index log; add KeyError + log tests

feat(bbb): expand SMILES → Morgan FP into model-ready DataFrame with drift logging

refactor(bbb): migrate to MorganGenerator API; consolidate test imports

feat(bbb): add Morgan fingerprint extraction with shape/dtype guarantees

refactor(bbb): tighten is_valid_smiles signature; document RDLogger global effect

feat(bbb): add SMILES validity guard with RDKit + test fixture

chore: bootstrap NeuroBridge project skeleton