test(e2e-http): parametrize compose runner by VECTOR_DB_TYPE / GRAPH_DB_TYPE + 2-combo CI matrix (#1740)

The compose runner ran a single fixed backend shape (Qdrant + PG-graph),
so the HTTP E2E suite only proved one of the two production deployment
shapes actually boots end-to-end. Connector-level swap correctness is
covered by tests/integration/compat (matrixed in compat-test.yml), but
that doesn't exercise the full FastAPI lifespan against the alternate
backends.

Changes:
- runners/compose/up.sh: accept VECTOR_DB_TYPE (qdrant|pgvector) and
  GRAPH_DB_TYPE (postgresql|neo4j|nebula); validate, idempotently rewrite
  .env so the api container picks them up, activate matching --profile.
  Defaults preserve historical behavior (qdrant + postgresql). qdrant is
  always included in the service set because the api container's
  depends_on requires it healthy regardless of vector backend selection.
- envs/docker.env.overrides: set PGVECTOR_DATABASE_URL to the same DSN as
  DATABASE_URL — required when VECTOR_DB_TYPE=pgvector, harmless when
  qdrant.
- Makefile: add test-http-smoke-compose-{lite,full} shortcuts for the two
  shapes (Lite = pgvector + postgresql, Full = qdrant + neo4j).
- .github/workflows/e2e-http-smoke.yml: convert e2e-http-smoke job to a
  fail-fast=false matrix over [lite, full]. Provider-aware job is
  unchanged (defaults), since LLM-provider coverage is orthogonal to
  graph backend choice and the matrix would double API-cost.

Author: earayu

.github/workflows/e2e-http-smoke.yml

@@ -15,6 +15,24 @@ jobs:
     timeout-minutes: 45
     permissions:
       contents: read
+    strategy:
+      fail-fast: false
+      # Two deployment-shape combos. Connector-level "swap one DB" coverage
+      # already lives in compat-test.yml's matrix (Qdrant/pgvector,
+      # PG/Neo4j/Nebula); this matrix exists to prove the full HTTP stack
+      # boots and runs end-to-end under each shape.
+      matrix:
+        combo:
+          - name: lite
+            vector: pgvector
+            graph: postgresql
+          - name: full
+            vector: qdrant
+            graph: neo4j
+    name: e2e-http-smoke (${{ matrix.combo.name }})
+    env:
+      VECTOR_DB_TYPE: ${{ matrix.combo.vector }}
+      GRAPH_DB_TYPE: ${{ matrix.combo.graph }}
     steps:
       - uses: actions/checkout@v4
 
@@ -53,7 +71,7 @@ jobs:
         if: failure()
         uses: actions/upload-artifact@v4
         with:
-          name: e2e-http-bootstrap-artifacts
+          name: e2e-http-bootstrap-artifacts-${{ matrix.combo.name }}
           path: tests/e2e_http/bootstrap/.generated
           if-no-files-found: ignore
           # The bootstrap directory name starts with "." — actions/upload-artifact@v4
@@ -64,8 +82,8 @@ jobs:
       - name: Dump Compose diagnostics on failure
         if: failure()
         run: |
-          docker compose -f docker-compose.yml ps || true
-          docker compose -f docker-compose.yml logs --no-color api postgres redis qdrant es || true
+          docker compose --profile neo4j --profile nebula -f docker-compose.yml ps || true
+          docker compose --profile neo4j --profile nebula -f docker-compose.yml logs --no-color || true
 
       - name: Stop Compose stack
         if: always()

Makefile

@@ -51,6 +51,7 @@ help:
 	@printf "  make test-http-full       Run full HTTP suite against an existing target\n"
 	@printf "  make test-http-up-compose / test-http-down-compose\n"
 	@printf "  make test-http-smoke-compose / test-http-full-compose\n"
+	@printf "  make test-http-smoke-compose-lite / test-http-smoke-compose-full   (DB-combo shortcuts)\n"
 	@printf "  make test-http-up-k8s / test-http-down-k8s\n"
 	@printf "  make test-http-smoke-k8s / test-http-full-k8s\n\n"
 	@printf "Build / API\n"
@@ -204,6 +205,7 @@ add-license:
 .PHONY: test-all test-unit test-integration test-e2e test-e2e-perf \
 	test-http-bootstrap test-http-smoke test-http-full \
 	test-http-up-compose test-http-down-compose test-http-smoke-compose test-http-full-compose \
+	test-http-smoke-compose-lite test-http-smoke-compose-full \
 	test-http-up-k8s test-http-down-k8s test-http-smoke-k8s test-http-full-k8s
 test-all: test-unit test-integration test-e2e
 
@@ -275,6 +277,18 @@ test-http-smoke-compose:
 test-http-full-compose:
 	@./tests/e2e_http/scripts/run_compose_full.sh
 
+# Backend-combo shortcuts. Lite = single-PG (pgvector + PG-graph) for the
+# ApeRAG-Lite deployment; Full = Qdrant vector + Neo4j graph for the
+# distributed deployment. Connector-level swap correctness is covered by
+# tests/integration/compat/* (see test-compat-graph / test-compat-vector).
+test-http-smoke-compose-lite:
+	@VECTOR_DB_TYPE=pgvector GRAPH_DB_TYPE=postgresql \
+		./tests/e2e_http/scripts/run_compose_smoke.sh
+
+test-http-smoke-compose-full:
+	@VECTOR_DB_TYPE=qdrant GRAPH_DB_TYPE=neo4j \
+		./tests/e2e_http/scripts/run_compose_smoke.sh
+
 test-http-up-k8s:
 	@./tests/e2e_http/runners/k8s/up.sh
 

envs/docker.env.overrides

@@ -8,6 +8,7 @@ NEBULA_USERNAME=root
 NEBULA_PASSWORD=nebula
 CELERY_BROKER_URL=redis://default:password@aperag-redis:6379/0
 DATABASE_URL="postgresql://postgres:postgres@aperag-postgres:5432/postgres"
+PGVECTOR_DATABASE_URL="postgresql://postgres:postgres@aperag-postgres:5432/postgres"
 VECTOR_DB_CONTEXT={"url":"http://aperag-qdrant", "port":6333, "distance":"Cosine", "timeout": 1000}
 ES_HOST=http://aperag-es:9200
 MEMORY_REDIS_URL=redis://default:password@aperag-redis:6379

tests/e2e_http/runners/compose/up.sh

@@ -5,19 +5,71 @@ ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../../.." && pwd)"
 cd "${ROOT_DIR}"
 
 E2E_BASE_URL="${E2E_BASE_URL:-http://127.0.0.1:8000}"
-E2E_COMPOSE_SERVICES="${E2E_COMPOSE_SERVICES:-postgres redis qdrant es api}"
 E2E_HEALTH_ATTEMPTS="${E2E_HEALTH_ATTEMPTS:-90}"
 E2E_HEALTH_SLEEP_SECONDS="${E2E_HEALTH_SLEEP_SECONDS:-2}"
 
+# Backend selection. Defaults preserve historical behavior (Qdrant + PG-graph).
+VECTOR_DB_TYPE="${VECTOR_DB_TYPE:-qdrant}"
+GRAPH_DB_TYPE="${GRAPH_DB_TYPE:-postgresql}"
+
+case "${VECTOR_DB_TYPE}" in
+  qdrant|pgvector) ;;
+  *)
+    echo "VECTOR_DB_TYPE must be one of: qdrant, pgvector (got '${VECTOR_DB_TYPE}')" >&2
+    exit 2
+    ;;
+esac
+
+case "${GRAPH_DB_TYPE}" in
+  postgresql|neo4j|nebula) ;;
+  *)
+    echo "GRAPH_DB_TYPE must be one of: postgresql, neo4j, nebula (got '${GRAPH_DB_TYPE}')" >&2
+    exit 2
+    ;;
+esac
+
+# Always include qdrant in the service set: the api container's depends_on
+# requires it healthy regardless of which vector backend is selected. Leaving
+# qdrant idle in pgvector mode is cheap and avoids docker-compose surgery.
+DEFAULT_SERVICES="postgres redis qdrant es api"
+E2E_COMPOSE_SERVICES="${E2E_COMPOSE_SERVICES:-${DEFAULT_SERVICES}}"
+
+profile_flags=()
+case "${GRAPH_DB_TYPE}" in
+  neo4j)  profile_flags=(--profile neo4j) ;;
+  nebula) profile_flags=(--profile nebula) ;;
+esac
+
 if [[ ! -f "${ROOT_DIR}/.env" ]]; then
   cp "${ROOT_DIR}/envs/env.template" "${ROOT_DIR}/.env"
 fi
 
-docker compose -f docker-compose.yml up -d --build ${E2E_COMPOSE_SERVICES}
+# Idempotently set or append a KEY=VALUE in .env so the api container's
+# env_file pickup reflects the selected backends.
+update_env_var() {
+  local key="$1"
+  local value="$2"
+  local file="${ROOT_DIR}/.env"
+  if grep -qE "^${key}=" "${file}"; then
+    awk -v k="${key}" -v v="${value}" 'BEGIN{FS=OFS="="} $1==k{print k"="v; next} {print}' \
+      "${file}" > "${file}.tmp"
+    mv "${file}.tmp" "${file}"
+  else
+    printf '\n%s=%s\n' "${key}" "${value}" >> "${file}"
+  fi
+}
+
+update_env_var VECTOR_DB_TYPE "${VECTOR_DB_TYPE}"
+update_env_var GRAPH_DB_TYPE "${GRAPH_DB_TYPE}"
+
+echo "Compose runner starting (vector=${VECTOR_DB_TYPE}, graph=${GRAPH_DB_TYPE}, profiles='${profile_flags[*]:-}')"
+
+# `${array[@]+"${array[@]}"}` is the set -u-safe expansion for an empty array.
+docker compose ${profile_flags[@]+"${profile_flags[@]}"} -f docker-compose.yml up -d --build ${E2E_COMPOSE_SERVICES}
 
 for ((i = 1; i <= E2E_HEALTH_ATTEMPTS; i++)); do
   if curl --silent --show-error --fail "${E2E_BASE_URL}/health" >/dev/null; then
-    echo "Compose runner ready at ${E2E_BASE_URL}"
+    echo "Compose runner ready at ${E2E_BASE_URL} (vector=${VECTOR_DB_TYPE}, graph=${GRAPH_DB_TYPE})"
     exit 0
   fi
   sleep "${E2E_HEALTH_SLEEP_SECONDS}"