8cafd9917f
Krok 1 planu docs/kb/modules/05-faza2-plan.md §3/§6 (chunk-level embeddings, 1:N do envelope). Addytywna — 001_envelope.sql nietknięta (zweryfikowane \d envelope po migracji: identyczny schemat + FK jako "Referenced by"). Schemat wg rekomendacji recon (§2 decyzja 1+2): osobna tabela (nie kolumna w envelope, bo N-wartościowy chunking jest obowiązkowy przy dokumentach >8k tokenów), embedding VECTOR(1024) pod bge-m3 (dense), HNSW cosine index, kolumna `model` do trywialnego re-indexu przy zmianie modelu (kb-00 zasada #1: indeks odtwarzalny). Idempotentna (CREATE TABLE/INDEX IF NOT EXISTS, zweryfikowane podwójnym uruchomieniem na kb-postgres@PIHA — drugi run same NOTICE "already exists, skipping"). Zastosowana na żywej bazie: ssh piha docker exec kb-postgres psql, po potwierdzeniu SQL przez Oskara. \dt + \d document_chunk + \d envelope zweryfikowane po migracji. Testy: dopisane sanity-testy 002 do packages/kb-mail/tests/test_migration.py (wzorzec 001 — statyczne assercje na treści SQL, bez DB), 13/13 zielone. Co NIE jest częścią tego kroku (§3 planu, odłożone): entity/entity_link (graf encji) — szkic na przyszłość, nie blokuje domknięcia modułu 5. Co dalej (plan §6, poza zakresem tego kroku): ollama pull bge-m3 na SOLARII, token API Paperless, jobs/gmail-header-backfill/, adapter Paperless→koperta, chunking+embed job. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
90 lines
3.1 KiB
Python
90 lines
3.1 KiB
Python
"""Sanity tests for SQL migration files — no DB or network required."""
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
REPO_ROOT = Path(__file__).parent.parent.parent.parent
|
|
INIT_DIR = REPO_ROOT / "services" / "kb-postgres" / "init"
|
|
|
|
|
|
def test_migration_001_exists():
|
|
assert (INIT_DIR / "001_envelope.sql").exists(), \
|
|
f"Expected {INIT_DIR / '001_envelope.sql'} to exist"
|
|
|
|
|
|
def test_migration_001_enables_vector_extension():
|
|
sql = (INIT_DIR / "001_envelope.sql").read_text()
|
|
assert "CREATE EXTENSION" in sql
|
|
assert "vector" in sql.lower()
|
|
|
|
|
|
def test_migration_001_creates_envelope_table():
|
|
sql = (INIT_DIR / "001_envelope.sql").read_text()
|
|
assert "CREATE TABLE" in sql
|
|
assert "envelope" in sql.lower()
|
|
|
|
|
|
def test_migration_001_has_all_frozen_columns():
|
|
sql = (INIT_DIR / "001_envelope.sql").read_text()
|
|
frozen_columns = ("id", "source", "ts", "geo", "raw_ref", "entities")
|
|
for col in frozen_columns:
|
|
assert col in sql, f"Frozen column '{col}' missing from 001_envelope.sql"
|
|
|
|
|
|
def test_migration_001_geo_is_nullable():
|
|
sql = (INIT_DIR / "001_envelope.sql").read_text()
|
|
# geo must NOT have NOT NULL constraint
|
|
lines = [l for l in sql.splitlines() if "geo" in l.lower()]
|
|
assert lines, "No 'geo' line found in migration SQL"
|
|
for line in lines:
|
|
assert "NOT NULL" not in line.upper(), \
|
|
f"geo must be nullable but found: {line.strip()}"
|
|
|
|
|
|
def test_migration_001_entities_has_default():
|
|
sql = (INIT_DIR / "001_envelope.sql").read_text()
|
|
lines = [l for l in sql.splitlines() if "entities" in l.lower()]
|
|
assert any("DEFAULT" in l.upper() for l in lines), \
|
|
"entities column must have a DEFAULT '[]'"
|
|
|
|
|
|
def test_migration_002_exists():
|
|
assert (INIT_DIR / "002_chunks.sql").exists(), \
|
|
f"Expected {INIT_DIR / '002_chunks.sql'} to exist"
|
|
|
|
|
|
def test_migration_002_does_not_touch_envelope():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
assert "ALTER TABLE envelope" not in sql
|
|
assert "DROP TABLE envelope" not in sql.upper()
|
|
|
|
|
|
def test_migration_002_creates_document_chunk_table():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
assert "CREATE TABLE IF NOT EXISTS document_chunk" in sql
|
|
|
|
|
|
def test_migration_002_references_envelope_with_cascade():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
assert "REFERENCES envelope(id) ON DELETE CASCADE" in sql
|
|
|
|
|
|
def test_migration_002_embedding_dimension_matches_bge_m3():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
# bge-m3 dense embedding dimension is 1024 (docs/kb/modules/05-faza2-plan.md §1.4)
|
|
assert "VECTOR(1024)" in sql.upper()
|
|
|
|
|
|
def test_migration_002_has_unique_envelope_chunk_index():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
assert "UNIQUE (envelope_id, chunk_index)" in sql
|
|
|
|
|
|
def test_migration_002_uses_idempotent_ddl():
|
|
sql = (INIT_DIR / "002_chunks.sql").read_text()
|
|
assert "CREATE TABLE IF NOT EXISTS" in sql
|
|
for line in sql.splitlines():
|
|
if line.strip().upper().startswith("CREATE INDEX"):
|
|
assert "IF NOT EXISTS" in line.upper(), \
|
|
f"CREATE INDEX must be idempotent: {line.strip()}"
|