bvandeusen
3610ba495f
Read cutover verified in prod (suggestions + allowlist read image_prediction; backfill complete at 908k rows / 51k images). Removes the old JSON column and everything that fed it: - ImageRecord.tagger_predictions column removed; migration 0046 DROPs it. tagger_model_version kept as the "tagged / current?" signal the backfill sweep reads (needs-tagging check switched to tagger_model_version IS NULL). - tag_and_embed no longer dual-writes the JSON — image_prediction is the only write path. - importer re-import reset drops the JSON line (image_prediction rows are already deleted on re-import). - Retired the one-time #768 backfill task + the #764 prune task, their admin endpoints, and their Maintenance cards (Backfill/PrunePredictionsCard). - Tests seed/assert via image_prediction; stale column refs removed. Disk reclaim is NOT automatic: DROP COLUMN is a catalog change. Run `VACUUM FULL image_record` off-hours afterward to return the ~100 GB to the OS so DB backups go small (#739). image_prediction (~90 MB) stays in pg_dump — it's the source of truth now. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
"""Smoke test for migration 0003: model classes import, schema shape correct."""
|
|
|
|
from backend.app.models import (
|
|
Base,
|
|
ImageRecord,
|
|
MLSettings,
|
|
TagAlias,
|
|
TagAllowlist,
|
|
TagReferenceEmbedding,
|
|
TagSuggestionRejection,
|
|
)
|
|
|
|
|
|
def test_new_tables_registered():
|
|
expected = {
|
|
"tag_allowlist",
|
|
"tag_suggestion_rejection",
|
|
"tag_alias",
|
|
"tag_reference_embedding",
|
|
"ml_settings",
|
|
}
|
|
assert expected.issubset(Base.metadata.tables.keys())
|
|
|
|
|
|
def test_image_record_columns_renamed():
|
|
cols = {c.name for c in ImageRecord.__table__.columns}
|
|
# tagger_predictions (the renamed wd14_predictions) was later dropped in
|
|
# migration 0046 — predictions live in image_prediction now (#768).
|
|
assert "tagger_model_version" in cols
|
|
assert "tagger_predictions" not in cols
|
|
assert "wd14_predictions" not in cols
|
|
assert "wd14_model_version" not in cols
|
|
|
|
|
|
def test_tag_alias_composite_pk():
|
|
pk_cols = {c.name for c in TagAlias.__table__.primary_key.columns}
|
|
assert pk_cols == {"alias_string", "alias_category"}
|
|
|
|
|
|
def test_ml_settings_singleton_constraint():
|
|
names = {c.name for c in MLSettings.__table__.constraints}
|
|
assert "ck_ml_settings_singleton" in names
|
|
|
|
|
|
def test_tag_reference_embedding_has_vector():
|
|
cols = {c.name for c in TagReferenceEmbedding.__table__.columns}
|
|
assert "embedding" in cols
|
|
assert "reference_count" in cols
|
|
|
|
|
|
def test_tag_allowlist_confidence_check():
|
|
names = {c.name for c in TagAllowlist.__table__.constraints}
|
|
assert "ck_tag_allowlist_confidence_range" in names
|
|
|
|
|
|
def test_tag_suggestion_rejection_pk():
|
|
pk_cols = {c.name for c in TagSuggestionRejection.__table__.primary_key.columns}
|
|
assert pk_cols == {"image_record_id", "tag_id"}
|