fix: overhaul the platform skeleton, add a serverless deployment track
An end-to-end audit found the repo could not build, test or run as shipped. This fixes every finding, then adds a Cloud Run track so the demo costs about £1/month idle instead of ~£150. CI (red on its first run) - api: setuptools could not build the package (flat layout with app/ and alembic/) - web: missing @types/node; `vitest run` exited 1 with no test files - pipeline: the stub run needed a gitignored VCF, and no process had a stub block - ruff pinned, mypy configured, DB tests on real Postgres (pgserver locally, service in CI) ML serving (scores were meaningless) - the registered model now carries its own feature engineering and returns predict_proba, so serving sends raw columns and cannot drift from training - resolve by registry alias (stages are deprecated in MLflow 3) and record the real version; re-scoring upserts instead of failing on the unique constraint - ClinVar labels parsed from VEP's lowercase terms Pipeline - exact ref/alt recovered from a CHROM_POS_REF_ALT VCF ID; loading is idempotent - job status reaches running/failed/succeeded, so the UI stops polling dead jobs - DATABASE_URL travels in the environment or a Nextflow secret, never on a command line - VEP cache and plugins staged as inputs; the gcp profile runs tasks on Google Batch Deployment - the API serves /api (matching the ingress); the web app reads its API URL at runtime - migrations run in an init container under a Postgres advisory lock - terraform: custom VPC shared with Batch, private Cloud SQL, API enablement, Workload Identity bindings, Secret Manager, deletion protection - serverless track, now the default: Cloud Run services scaling to zero, a Cloud Run job for the Nextflow driver, and Neon or Cloud SQL behind one DATABASE_URL secret. GKE and Argo remain, behind -var deploy_kubernetes=true. See docs/cloud.md. Correctness and security - 409 on duplicate sample names, 422 on bad paging, natural chromosome ordering, wider VEP text columns, enum dropped on downgrade, the sample's assembly actually used - vcf_uri restricted to gs:// objects or files under the data root, blocking option injection - CORS restricted to configured origins; `make down` no longer deletes volumes Data - docs/data.md records the peer-reviewed, openly licensed sources (GIAB HG002, ClinVar, gnomAD) with citations and an honest evaluation plan; `make data` fetches a chr22 slice Verified: api 50 tests, ml 18, loader 16, web 12; ruff, mypy, svelte-check, terraform validate and both kustomize overlays clean.
This commit is contained in:
+23
-2
@@ -2,8 +2,8 @@ import asyncio
|
||||
from logging.config import fileConfig
|
||||
|
||||
from alembic import context
|
||||
from sqlalchemy.ext.asyncio import async_engine_from_config
|
||||
from sqlalchemy import pool
|
||||
from sqlalchemy.ext.asyncio import async_engine_from_config
|
||||
|
||||
from app.config import settings
|
||||
from app.models import Base
|
||||
@@ -14,10 +14,15 @@ if config.config_file_name:
|
||||
fileConfig(config.config_file_name)
|
||||
target_metadata = Base.metadata
|
||||
|
||||
# Arbitrary constant shared by every `alembic upgrade` (one per API replica's init container).
|
||||
MIGRATION_LOCK_ID = 72150001
|
||||
|
||||
|
||||
def run_migrations(connection):
|
||||
context.configure(connection=connection, target_metadata=target_metadata)
|
||||
with context.begin_transaction():
|
||||
# Held until this transaction commits; a concurrent run waits, then finds nothing to do.
|
||||
connection.exec_driver_sql(f"SELECT pg_advisory_xact_lock({MIGRATION_LOCK_ID})")
|
||||
context.run_migrations()
|
||||
|
||||
|
||||
@@ -27,6 +32,22 @@ async def run_async():
|
||||
)
|
||||
async with engine.connect() as conn:
|
||||
await conn.run_sync(run_migrations)
|
||||
await engine.dispose()
|
||||
|
||||
|
||||
asyncio.run(run_async())
|
||||
def run_offline():
|
||||
"""`alembic upgrade head --sql`: emit the SQL instead of running it."""
|
||||
context.configure(
|
||||
url=settings.database_url,
|
||||
target_metadata=target_metadata,
|
||||
literal_binds=True,
|
||||
dialect_opts={"paramstyle": "named"},
|
||||
)
|
||||
with context.begin_transaction():
|
||||
context.run_migrations()
|
||||
|
||||
|
||||
if context.is_offline_mode():
|
||||
run_offline()
|
||||
else:
|
||||
asyncio.run(run_async())
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
"""widen VEP text columns
|
||||
|
||||
VEP joins multiple consequences with "&" and co-located ClinVar significances with ",", which
|
||||
overflowed VARCHAR(120) and aborted the whole load transaction.
|
||||
|
||||
Revision ID: 5f2c8e1b9d04
|
||||
Revises: a3e9ead256a5
|
||||
Create Date: 2026-09-11 18:00:00.000000
|
||||
|
||||
"""
|
||||
from collections.abc import Sequence
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
revision: str = '5f2c8e1b9d04'
|
||||
down_revision: str | None = 'a3e9ead256a5'
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
COLUMNS = ('consequence', 'clinvar_sig')
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
for column in COLUMNS:
|
||||
op.alter_column('variants', column, type_=sa.Text(), existing_type=sa.String(length=120))
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
for column in COLUMNS:
|
||||
op.alter_column(
|
||||
'variants', column, type_=sa.String(length=120), existing_type=sa.Text(),
|
||||
postgresql_using=f'left({column}, 120)',
|
||||
)
|
||||
@@ -5,17 +5,17 @@ Revises:
|
||||
Create Date: 2026-09-11 15:36:04.335440
|
||||
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
from collections.abc import Sequence
|
||||
|
||||
from alembic import op
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = 'a3e9ead256a5'
|
||||
down_revision: Union[str, None] = None
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
down_revision: str | None = None
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
@@ -87,4 +87,7 @@ def downgrade() -> None:
|
||||
op.drop_table('variants')
|
||||
op.drop_table('jobs')
|
||||
op.drop_table('samples')
|
||||
# ### end Alembic commands ###
|
||||
# ### end Alembic commands ###
|
||||
# Autogenerate does not drop the type created by sa.Enum; without this, upgrading again
|
||||
# fails with "type jobstatus already exists".
|
||||
sa.Enum(name='jobstatus').drop(op.get_bind(), checkfirst=True)
|
||||
Reference in New Issue
Block a user