test(rlsapi): add initial e2e test for v1 infer endpoint

.github/workflows/e2e_tests.yaml

@@ -135,9 +135,9 @@ jobs:
         run: |
           CONFIGS_DIR="tests/e2e/configs"
           ENVIRONMENT="$CONFIG_ENVIRONMENT"
-          
+
           echo "Looking for configurations in $CONFIGS_DIR/"
-          
+
           # List available configurations
           if [ -d "$CONFIGS_DIR" ]; then
             echo "Available configurations:"
@@ -146,12 +146,12 @@ jobs:
             echo "Configs directory '$CONFIGS_DIR' not found!"
             exit 1
           fi
-          
+
           # Determine which config file to use
           CONFIG_FILE="$CONFIGS_DIR/run-$ENVIRONMENT.yaml"
-          
+
           echo "Looking for: $CONFIG_FILE"
-          
+
           if [ -f "$CONFIG_FILE" ]; then
             echo "✅ Found config for environment: $ENVIRONMENT"
             cp "$CONFIG_FILE" run.yaml
@@ -163,6 +163,30 @@ jobs:
             exit 1
           fi
 
+      - name: Set default model for rlsapi v1 tests
+        run: |
+          # Set default model/provider for rlsapi v1 endpoint based on environment
+          case "${{ matrix.environment }}" in
+            ci)
+              echo "E2E_DEFAULT_PROVIDER=openai" >> $GITHUB_ENV
+              echo "E2E_DEFAULT_MODEL=gpt-4o-mini" >> $GITHUB_ENV
+              ;;
+            azure)
+              echo "E2E_DEFAULT_PROVIDER=azure" >> $GITHUB_ENV
+              echo "E2E_DEFAULT_MODEL=gpt-4o-mini" >> $GITHUB_ENV
+              ;;
+            vertexai)
+              echo "E2E_DEFAULT_PROVIDER=google-vertex" >> $GITHUB_ENV
+              echo "E2E_DEFAULT_MODEL=gemini-2.0-flash-exp" >> $GITHUB_ENV
+              ;;
+            *)
+              echo "⚠️ Unknown environment: ${{ matrix.environment }}, using defaults"
+              echo "E2E_DEFAULT_PROVIDER=openai" >> $GITHUB_ENV
+              echo "E2E_DEFAULT_MODEL=gpt-4o-mini" >> $GITHUB_ENV
+              ;;
+          esac
+          echo "✅ Set E2E_DEFAULT_PROVIDER=${E2E_DEFAULT_PROVIDER} and E2E_DEFAULT_MODEL=${E2E_DEFAULT_MODEL}"
+
       - name: Show final configuration
         run: |
           echo "=== Configuration Summary ==="

docker-compose-library.yaml

@@ -19,6 +19,9 @@ services:
       # OpenAI
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - E2E_OPENAI_MODEL=${E2E_OPENAI_MODEL:-gpt-4-turbo}
+      # Default model for rlsapi v1 tests
+      - E2E_DEFAULT_PROVIDER=${E2E_DEFAULT_PROVIDER:-openai}
+      - E2E_DEFAULT_MODEL=${E2E_DEFAULT_MODEL:-gpt-4o-mini}
       # Azure
       - AZURE_API_KEY=${AZURE_API_KEY:-}
       # RHAIIS

docker-compose.yaml

@@ -55,6 +55,9 @@ services:
     environment:
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - AZURE_API_KEY=${AZURE_API_KEY}
+      # Default model for rlsapi v1 tests
+      - E2E_DEFAULT_PROVIDER=${E2E_DEFAULT_PROVIDER:-openai}
+      - E2E_DEFAULT_MODEL=${E2E_DEFAULT_MODEL:-gpt-4o-mini}
     depends_on:
         llama-stack:
           condition: service_healthy

tests/e2e/configuration/library-mode/lightspeed-stack-rlsapi.yaml

@@ -0,0 +1,24 @@
+name: Lightspeed Core Service (LCS)
+service:
+  host: 0.0.0.0
+  port: 8080
+  auth_enabled: false
+  workers: 1
+  color_log: true
+  access_log: true
+llama_stack:
+  # Library mode - embeds llama-stack as library
+  use_as_library_client: true
+  library_client_config_path: run.yaml
+user_data_collection:
+  feedback_enabled: true
+  feedback_storage: "/tmp/data/feedback"
+  transcripts_enabled: true
+  transcripts_storage: "/tmp/data/transcripts"
+authentication:
+  module: "noop"
+inference:
+  # Configure default model/provider for rlsapi v1 endpoint
+  # These are set per-environment in the CI workflow
+  default_provider: ${env.E2E_DEFAULT_PROVIDER:=openai}
+  default_model: ${env.E2E_DEFAULT_MODEL:=gpt-4o-mini}

tests/e2e/configuration/library-mode/lightspeed-stack.yaml

@@ -16,4 +16,4 @@ user_data_collection:
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
 authentication:
-  module: "noop"
+  module: "noop"

tests/e2e/configuration/server-mode/lightspeed-stack-rlsapi.yaml

@@ -0,0 +1,25 @@
+name: Lightspeed Core Service (LCS)
+service:
+  host: 0.0.0.0
+  port: 8080
+  auth_enabled: false
+  workers: 1
+  color_log: true
+  access_log: true
+llama_stack:
+  # Server mode - connects to separate llama-stack service
+  use_as_library_client: false
+  url: http://llama-stack:8321
+  api_key: xyzzy
+user_data_collection:
+  feedback_enabled: true
+  feedback_storage: "/tmp/data/feedback"
+  transcripts_enabled: true
+  transcripts_storage: "/tmp/data/transcripts"
+authentication:
+  module: "noop"
+inference:
+  # Configure default model/provider for rlsapi v1 endpoint
+  # These are set per-environment in the CI workflow
+  default_provider: ${env.E2E_DEFAULT_PROVIDER:=openai}
+  default_model: ${env.E2E_DEFAULT_MODEL:=gpt-4o-mini}

tests/e2e/configuration/server-mode/lightspeed-stack.yaml

@@ -17,4 +17,4 @@ user_data_collection:
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
 authentication:
-  module: "noop"
+  module: "noop"

tests/e2e/features/environment.py

@@ -171,6 +171,15 @@ def before_feature(context: Context, feature: Feature) -> None:
         switch_config(context.feature_config)
         restart_container("lightspeed-stack")
 
+    if "RlsapiConfig" in feature.tags:
+        mode_dir = "library-mode" if context.is_library_mode else "server-mode"
+        context.feature_config = (
+            f"tests/e2e/configuration/{mode_dir}/lightspeed-stack-rlsapi.yaml"
+        )
+        context.default_config_backup = create_config_backup("lightspeed-stack.yaml")
+        switch_config(context.feature_config)
+        restart_container("lightspeed-stack")
+
     if "Feedback" in feature.tags:
         context.hostname = os.getenv("E2E_LSC_HOSTNAME", "localhost")
         context.port = os.getenv("E2E_LSC_PORT", "8080")
@@ -184,6 +193,11 @@ def after_feature(context: Context, feature: Feature) -> None:
         restart_container("lightspeed-stack")
         remove_config_backup(context.default_config_backup)
 
+    if "RlsapiConfig" in feature.tags:
+        switch_config(context.default_config_backup)
+        restart_container("lightspeed-stack")
+        remove_config_backup(context.default_config_backup)
+
     if "Feedback" in feature.tags:
         for conversation_id in context.feedback_conversations:
             url = f"http://{context.hostname}:{context.port}/v1/conversations/{conversation_id}"

tests/e2e/features/rlsapi_v1.feature

@@ -0,0 +1,16 @@
+@RlsapiConfig
+Feature: RLSAPI v1 infer endpoint
+  Basic tests for the RLSAPI v1 inference endpoint.
+
+  Background:
+    Given The service is started locally
+      And REST API service prefix is /v1
+
+  Scenario: Verify RLSAPI v1 infer endpoint returns 200
+    Given The system is in default state
+     When I access REST API endpoint "infer" using HTTP POST method
+      """
+      {"question": "Say hello"}
+      """
+     Then The status code of the response is 200
+      And Content type of response should be set to "application/json"

tests/e2e/test_list.txt

@@ -9,3 +9,4 @@ features/info.feature
 features/query.feature
 features/streaming_query.feature
 features/rest_api.feature
+features/rlsapi_v1.feature