Adding explicit TLS output checks

Author: asimurka

tests/e2e/features/tls.feature

@@ -21,6 +21,7 @@ Feature: TLS configuration for remote inference providers
     {"query": "Say hello", "model": "mock-tls-model", "provider": "tls-openai"}
     """
      Then The status code of the response is 200
+      And The body of the response contains Hello from the TLS mock inference server
 
   Scenario: Inference succeeds with CA certificate verification
     Given Llama Stack is configured with CA certificate verification
@@ -31,6 +32,7 @@ Feature: TLS configuration for remote inference providers
     {"query": "Say hello", "model": "mock-tls-model", "provider": "tls-openai"}
     """
      Then The status code of the response is 200
+      And The body of the response contains Hello from the TLS mock inference server
 
   Scenario: Inference fails with an untrusted CA certificate
     Given Llama Stack is configured with CA certificate path "/certs/untrusted-ca.crt"
@@ -74,6 +76,7 @@ Feature: TLS configuration for remote inference providers
     {"query": "Say hello", "model": "mock-tls-model", "provider": "tls-openai"}
     """
      Then The status code of the response is 200
+      And The body of the response contains Hello from the TLS mock inference server
 
   Scenario: Inference fails when mTLS is required but no client certificate is provided
     Given Llama Stack is configured for mTLS without client certificate
@@ -150,6 +153,7 @@ Feature: TLS configuration for remote inference providers
     {"query": "Say hello", "model": "mock-tls-model", "provider": "tls-openai"}
     """
      Then The status code of the response is 200
+      And The body of the response contains Hello from the TLS mock inference server
 
   Scenario: Inference fails with TLS minimum version TLSv1.3 and untrusted CA certificate
     Given Llama Stack is configured with TLS minimum version "TLSv1.3" and CA certificate path "/certs/untrusted-ca.crt"

tests/e2e/mock_tls_inference_server/server.py

@@ -75,10 +75,49 @@ def do_POST(self) -> None:  # pylint: disable=invalid-name
             request_data = {}
 
         model = request_data.get("model", MODEL_ID)
+        completion_id = "chatcmpl-tls-test-001"
+        response_text = "Hello from the TLS mock inference server."
+
+        # Llama Stack calls remote chat completions with stream=True and reads
+        # assistant text from delta.content chunks.
+        if request_data.get("stream"):
+            self.send_response(200)
+            self.send_header("Content-Type", "text/event-stream")
+            self.send_header("Cache-Control", "no-cache")
+            self.end_headers()
+            content_chunk = {
+                "id": completion_id,
+                "object": "chat.completion.chunk",
+                "created": 1700000000,
+                "model": model,
+                "choices": [
+                    {
+                        "index": 0,
+                        "delta": {"role": "assistant", "content": response_text},
+                        "finish_reason": None,
+                    }
+                ],
+            }
+            self.wfile.write(f"data: {json.dumps(content_chunk)}\n\n".encode())
+            finish_chunk = {
+                "id": completion_id,
+                "object": "chat.completion.chunk",
+                "created": 1700000000,
+                "model": model,
+                "choices": [{"index": 0, "delta": {}, "finish_reason": "stop"}],
+                "usage": {
+                    "prompt_tokens": 8,
+                    "completion_tokens": 9,
+                    "total_tokens": 17,
+                },
+            }
+            self.wfile.write(f"data: {json.dumps(finish_chunk)}\n\n".encode())
+            self.wfile.write(b"data: [DONE]\n\n")
+            return
 
         self._send_json(
             {
-                "id": "chatcmpl-tls-test-001",
+                "id": completion_id,
                 "object": "chat.completion",
                 "created": 1700000000,
                 "model": model,
@@ -87,7 +126,7 @@ def do_POST(self) -> None:  # pylint: disable=invalid-name
                         "index": 0,
                         "message": {
                             "role": "assistant",
-                            "content": "Hello from the TLS mock inference server.",
+                            "content": response_text,
                         },
                         "finish_reason": "stop",
                     }