Move database layer to SQLAlchemy and Alembic

.github/workflows/azure-deploy.yml

@@ -53,6 +53,34 @@ jobs:
           echo "image_uri=${IMAGE_URI}" >> "$GITHUB_OUTPUT"
           echo "Deploying ${IMAGE_URI}"
 
+      - name: Check out deployed commit
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.workflow_run.head_sha || github.sha }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install migration dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e .
+
+      - name: Run database migrations
+        shell: bash
+        run: |
+          DATABASE_URL="$(az containerapp secret show \
+            --name "$AZURE_CONTAINER_APP" \
+            --resource-group "$AZURE_RESOURCE_GROUP" \
+            --secret-name database-url \
+            --query value \
+            --output tsv)"
+          echo "::add-mask::${DATABASE_URL}"
+          export DATABASE_URL
+          alembic upgrade head
+
       - name: Update Azure Container App
         run: |
           az containerapp update \

.github/workflows/ci.yml

@@ -11,6 +11,30 @@ jobs:
     name: Backend tests
     runs-on: ubuntu-latest
 
+    services:
+      postgres:
+        image: pgvector/pgvector:pg16
+        env:
+          POSTGRES_USER: supportagent
+          POSTGRES_PASSWORD: supportagent
+          POSTGRES_DB: supportagent
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd "pg_isready -U supportagent"
+          --health-interval 5s
+          --health-timeout 5s
+          --health-retries 10
+
+    env:
+      CHAT_MODEL: qwen-plus
+      CHAT_MODELS: qwen-plus,qwen-max,qwen3-max
+      EMBEDDING_API_KEY: ci-placeholder
+      EMBEDDING_BASE_URL: https://example.invalid/v1
+      DATABASE_URL: postgresql://supportagent:supportagent@localhost:5432/supportagent
+      TEST_DATABASE_URL: postgresql://supportagent:supportagent@localhost:5432/supportagent_test
+      MCP_DYNAMIC_TOOLS_ENABLED: "false"
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -29,15 +53,11 @@ jobs:
         run: python -m compileall -q src/backend/supportagent
 
       - name: Run backend tests
-        env:
-          CHAT_MODEL: qwen-plus
-          CHAT_MODELS: qwen-plus,qwen-max,qwen3-max
-          EMBEDDING_API_KEY: ci-placeholder
-          EMBEDDING_BASE_URL: https://example.invalid/v1
-          DATABASE_URL: postgresql://supportagent:supportagent@localhost:5432/supportagent
-          MCP_DYNAMIC_TOOLS_ENABLED: "false"
         run: python -m pytest
 
+      - name: Run integration tests
+        run: python -m pytest tests/integration --run-integration --deselect tests/integration/storage
+
       - name: Run offline claim evaluation
         run: |
           python -m supportagent.evaluation \

alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url =
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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

migrations/README

@@ -0,0 +1 @@
+Generic single-database configuration.

migrations/env.py

@@ -0,0 +1,28 @@
+from logging.config import fileConfig
+
+from alembic import context
+
+from supportagent.db import models  # noqa: F401
+from supportagent.db.base import Base
+from supportagent.db.session import engine
+
+config = context.config
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+target_metadata = Base.metadata
+
+
+def run_migrations_online() -> None:
+    with engine.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            compare_type=True,
+            compare_server_default=True,
+        )
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+run_migrations_online()

migrations/script.py.mako

@@ -0,0 +1,29 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy  # noqa: F401
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[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:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

migrations/versions/0fdad45ad4f7_add_hnsw_index_on_chunk_embeddings.py

@@ -0,0 +1,33 @@
+"""Add HNSW index on chunk embeddings
+
+Revision ID: 0fdad45ad4f7
+Revises: 267f87b25a77
+Create Date: 2026-10-29 15:22:51.359910
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy  # noqa: F401
+
+
+# revision identifiers, used by Alembic.
+revision: str = '0fdad45ad4f7'
+down_revision: Union[str, Sequence[str], None] = '267f87b25a77'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_index('chunks_embedding_hnsw_idx', 'chunks', ['embedding'], unique=False, postgresql_using='hnsw', postgresql_ops={'embedding': 'vector_cosine_ops'})
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index('chunks_embedding_hnsw_idx', table_name='chunks', postgresql_using='hnsw', postgresql_ops={'embedding': 'vector_cosine_ops'})
+    # ### end Alembic commands ###