Feat/postgresql migration

.env.example

@@ -46,8 +46,9 @@ LITELLM_FALLBACK_MODEL=               # Optional fallback model (empty = no fall
 MAX_CONCURRENT_REVIEWS=5
 RATE_LIMIT_RPM=60
 
-# Storage (SQLite by default; replace with PostgreSQL URL for production)
-DATABASE_URL=sqlite+aiosqlite:////data/d1ff.db
+# PostgreSQL (default connects to docker-compose postgres service)
+# For external DB: DATABASE_URL=postgresql+asyncpg://user:pass@host:5432/dbname
+DATABASE_URL=postgresql+asyncpg://d1ff:d1ff_local@postgres:5432/d1ff
 
 # Observability
 LOG_LEVEL=INFO  # Options: DEBUG, INFO, WARNING, ERROR

.github/workflows/ci.yml

@@ -15,6 +15,5 @@ jobs:
         with:
           python-version: "3.12"
       - run: uv sync
-      - run: uv run ruff check .
       - run: uv run mypy src/
       - run: uv run pytest

.pre-commit-config.yaml

@@ -1,10 +1,4 @@
 repos:
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.4
-    hooks:
-      - id: ruff
-        args: [--fix]
-      - id: ruff-format
   - repo: local
     hooks:
       - id: mypy
@@ -14,6 +8,7 @@ repos:
         types: [python]
         pass_filenames: false
         args: [src/]
+        stages: [pre-push]
       - id: pytest
         name: pytest
         entry: uv run pytest

Dockerfile

@@ -44,7 +44,10 @@ COPY --from=backend-builder /app/prompts /app/prompts
 # Copy compiled React SPA from frontend-builder
 COPY --from=frontend-builder /frontend/dist /app/static
 
-# Create volume mount point for SQLite
+# Copy Alembic config and migrations
+COPY alembic.ini ./
+COPY alembic/ ./alembic/
+
 RUN mkdir -p /data
 
 ENV PORT=8000

alembic.ini

@@ -0,0 +1,35 @@
+[alembic]
+script_location = alembic
+
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/env.py

@@ -0,0 +1,45 @@
+"""Alembic environment configuration for async PostgreSQL."""
+
+import asyncio
+from logging.config import fileConfig
+
+from sqlalchemy import pool
+from sqlalchemy.ext.asyncio import create_async_engine
+
+from alembic import context
+from d1ff.storage.schema import metadata
+
+config = context.config
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+target_metadata = metadata
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode — generates SQL script."""
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(url=url, target_metadata=target_metadata, literal_binds=True)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_migrations_online() -> None:
+    """Run migrations in 'online' mode — connects to database via asyncpg."""
+    url = config.get_main_option("sqlalchemy.url")
+    connectable = create_async_engine(url, poolclass=pool.NullPool)
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+    await connectable.dispose()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    asyncio.run(run_migrations_online())

alembic/script.py.mako

@@ -0,0 +1,25 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

alembic/versions/001_initial_schema.py

@@ -0,0 +1,138 @@
+"""Initial schema with all tables and pgvector extension.
+
+Revision ID: 001
+Revises:
+Create Date: 2026-03-29
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+
+from alembic import op
+
+revision: str = "001"
+down_revision: str | None = None
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.execute("CREATE EXTENSION IF NOT EXISTS vector")
+
+    op.create_table(
+        "installations",
+        sa.Column("installation_id", sa.Integer, primary_key=True, autoincrement=False),
+        sa.Column("account_login", sa.Text, nullable=False),
+        sa.Column("account_type", sa.Text, nullable=False),
+        sa.Column("suspended", sa.Boolean, nullable=False, server_default="false"),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+    )
+
+    op.create_table(
+        "api_keys",
+        sa.Column("id", sa.Integer, primary_key=True, autoincrement=True),
+        sa.Column(
+            "installation_id",
+            sa.Integer,
+            sa.ForeignKey("installations.installation_id"),
+            nullable=False,
+        ),
+        sa.Column("provider", sa.Text, nullable=False),
+        sa.Column("model", sa.Text, nullable=False),
+        sa.Column("encrypted_key", sa.Text, nullable=False),
+        sa.Column("custom_endpoint", sa.Text),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.UniqueConstraint("installation_id", "provider"),
+    )
+
+    op.create_table(
+        "repositories",
+        sa.Column("id", sa.Integer, primary_key=True, autoincrement=False),
+        sa.Column(
+            "installation_id",
+            sa.Integer,
+            sa.ForeignKey("installations.installation_id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("repo_name", sa.Text, nullable=False),
+        sa.Column("full_name", sa.Text, nullable=False),
+        sa.Column("private", sa.Boolean, nullable=False, server_default="false"),
+        sa.Column(
+            "created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.func.now()
+        ),
+    )
+
+    op.create_table(
+        "pr_states",
+        sa.Column("installation_id", sa.Integer, nullable=False),
+        sa.Column("repo_full_name", sa.Text, nullable=False),
+        sa.Column("pr_number", sa.Integer, nullable=False),
+        sa.Column("state", sa.Text, nullable=False, server_default="active"),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.PrimaryKeyConstraint("installation_id", "repo_full_name", "pr_number"),
+    )
+
+    op.create_table(
+        "feedback_reactions",
+        sa.Column("id", sa.Integer, primary_key=True, autoincrement=True),
+        sa.Column("comment_id", sa.Integer, nullable=False),
+        sa.Column("reaction_type", sa.Text, nullable=False),
+        sa.Column("installation_id", sa.Integer, nullable=False),
+        sa.Column("pr_number", sa.Integer, nullable=False),
+        sa.Column("repo_full_name", sa.Text, nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+    )
+
+    op.create_table(
+        "users",
+        sa.Column("id", sa.Integer, primary_key=True, autoincrement=True),
+        sa.Column("github_id", sa.Integer, unique=True, nullable=False),
+        sa.Column("login", sa.Text, nullable=False),
+        sa.Column("email", sa.Text),
+        sa.Column("avatar_url", sa.Text),
+        sa.Column("encrypted_token", sa.Text, nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+    )
+
+    op.create_table(
+        "user_installations",
+        sa.Column(
+            "user_id", sa.Integer, sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False
+        ),
+        sa.Column(
+            "installation_id",
+            sa.Integer,
+            sa.ForeignKey("installations.installation_id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("user_id", "installation_id"),
+    )
+
+    op.create_table(
+        "user_global_settings",
+        sa.Column(
+            "user_id", sa.Integer, sa.ForeignKey("users.id", ondelete="CASCADE"), primary_key=True
+        ),
+        sa.Column("provider", sa.Text, nullable=False),
+        sa.Column("model", sa.Text, nullable=False),
+        sa.Column("encrypted_api_key", sa.Text, nullable=False),
+        sa.Column("custom_endpoint", sa.Text),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("user_global_settings")
+    op.drop_table("user_installations")
+    op.drop_table("users")
+    op.drop_table("feedback_reactions")
+    op.drop_table("pr_states")
+    op.drop_table("repositories")
+    op.drop_table("api_keys")
+    op.drop_table("installations")
+    op.execute("DROP EXTENSION IF EXISTS vector")

docker-compose.yml

@@ -3,34 +3,35 @@
 # 1. Build the image:
 #    docker build -t d1ff .
 #
-# 2. Run the container (requires a valid .env file with required vars set):
-#    docker run -v d1ff-data:/data -p 8000:8000 --env-file .env d1ff
-#
-#    For Docker-infra-only smoke testing (stub values to bypass fail-fast):
-#    docker run -v d1ff-data:/data -p 8000:8000 \
-#      -e GITHUB_APP_ID=1 \
-#      -e GITHUB_PRIVATE_KEY="-----BEGIN RSA PRIVATE KEY-----\nMIIEowIBAAKCAQEA0Z3VS5JJcds3xHn/ygWep4PAtEsHAcMCRCTxHFWkWgvMbOar\n-----END RSA PRIVATE KEY-----" \
-#      -e GITHUB_WEBHOOK_SECRET=test \
-#      -e ENCRYPTION_KEY=$(python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())") \
-#      d1ff
+# 2. Run the stack:
+#    docker compose up -d
 #
 # 3. Verify health endpoint responds:
 #    curl http://localhost:8000/health
 #    Expected: JSON with subsystem statuses, HTTP 200
-#
-# 4. Verify Docker healthcheck status (after start_period of 15s):
-#    docker inspect <container_id> --format='{{.State.Health.Status}}'
-#    Expected: "healthy"
 
 services:
+  postgres:
+    image: pgvector/pgvector:pg17
+    volumes:
+      - postgres-data:/var/lib/postgresql/data
+    environment:
+      POSTGRES_DB: d1ff
+      POSTGRES_USER: d1ff
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-d1ff_local}
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U d1ff"]
+      interval: 5s
+      timeout: 3s
+      retries: 5
+
   d1ff:
     build: .
-    # Or use a pre-built image:
-    # image: ghcr.io/d1ff-dev/d1ff:latest
     ports:
       - "8000:8000"
-    volumes:
-      - d1ff-data:/data
+    depends_on:
+      postgres:
+        condition: service_healthy
     env_file:
       - .env
     restart: unless-stopped
@@ -42,4 +43,4 @@ services:
       start_period: 15s
 
 volumes:
-  d1ff-data:
+  postgres-data: