LCORE-1422: Add streaming and responses API inline RAG e2e tests

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: are-ces

tests/e2e/features/environment.py

@@ -445,6 +445,7 @@ def before_feature(context: Context, feature: Feature) -> None:
         switch_config(context.feature_config)
         restart_container("lightspeed-stack")
 
+
 def after_feature(context: Context, feature: Feature) -> None:
     """Run after each feature file is exercised.
 

tests/e2e/features/inline_rag.feature

@@ -41,3 +41,28 @@ Feature: Inline RAG (BYOK) support tests
     """
     Then The status code of the response is 200
      And The response should contain non-empty referenced_documents
+
+  Scenario: Streaming query with inline RAG returns relevant content
+    Given The system is in default state
+      And I set the Authorization header to Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6Ikpva
+    When I use "streaming_query" to ask question with authorization header
+    """
+    {"query": "What is the title of the article from Paul?", "system_prompt": "You are an assistant. Write only lowercase letters"}
+    """
+    Then The status code of the response is 200
+     And I wait for the response to be completed
+     And The streamed response should contain following fragments
+         | Fragments in LLM response |
+         | great work                |
+
+  Scenario: Responses API with inline RAG returns relevant content
+    Given The system is in default state
+      And I set the Authorization header to Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6Ikpva
+    When I use "responses" to ask question with authorization header
+    """
+    {"input": "What is the title of the article from Paul?", "model": "{PROVIDER}/{MODEL}", "stream": false, "instructions": "You are an assistant. Write only lowercase letters"}
+    """
+    Then The status code of the response is 200
+     And The response should contain following fragments
+         | Fragments in LLM response |
+         | great work                |

tests/e2e/features/steps/llm_query_response.py

@@ -173,7 +173,21 @@ def check_fragments_in_response(context: Context) -> None:
     """
     assert context.response is not None
     response_json = context.response.json()
-    response = response_json["response"]
+
+    # Support both query endpoint format (response field) and responses API format (output array)
+    if "response" in response_json:
+        response = response_json["response"]
+    else:
+        # Responses API format: extract text from output messages
+        response = " ".join(
+            part.get("text", "")
+            for item in response_json.get("output", [])
+            if item.get("type") == "message"
+            for part in (
+                item.get("content") if isinstance(item.get("content"), list) else []
+            )
+            if part.get("type") == "output_text"
+        )
 
     assert context.table is not None, "Fragments are not specified in table"