From 36ddb962d874509dd2aa5fbba20edcd71578e689 Mon Sep 17 00:00:00 2001
From: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
Date: Fri, 23 Feb 2024 10:09:19 +0100
Subject: [PATCH] server: tests: parallel fix server is started twice, add
 colors to help to monitor in the CI jobs

---
 examples/server/tests/features/environment.py   | 1 +
 examples/server/tests/features/parallel.feature | 9 +--------
 examples/server/tests/features/steps/steps.py   | 2 +-
 3 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/examples/server/tests/features/environment.py b/examples/server/tests/features/environment.py
index 01877cd10d486..de2f9c9828d02 100644
--- a/examples/server/tests/features/environment.py
+++ b/examples/server/tests/features/environment.py
@@ -8,6 +8,7 @@
 
 
 def before_scenario(context, scenario):
+    print(f"\x1b[33;42mStarting new scenario: {scenario.name}!\x1b[0m")
     port = 8080
     if 'PORT' in os.environ:
         port = int(os.environ['PORT'])
diff --git a/examples/server/tests/features/parallel.feature b/examples/server/tests/features/parallel.feature
index d4d403eade843..07be39ef58a4b 100644
--- a/examples/server/tests/features/parallel.feature
+++ b/examples/server/tests/features/parallel.feature
@@ -50,17 +50,10 @@ Feature: Parallel
     Then all prompts are predicted with <n_predict> tokens
     Examples:
       | streaming | n_predict |
-      | disabled  | 64       |
+      | disabled  | 128       |
       #| enabled   | 64       | FIXME: phymbert: need to investigate why in aiohttp with streaming only one token is generated
 
   Scenario:  Multi users with total number of tokens to predict exceeds the KV Cache size #3969
-    Given a server listening on localhost:8080
-    And   a model file stories260K.gguf
-    And   42 as server seed
-    And   2 slots
-    And   64 KV cache size
-    Then  the server is starting
-    Then  the server is healthy
     Given a prompt:
       """
       Write a very long story about AI.
diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py
index 7375fcba92a5c..cfe03e799c2e7 100644
--- a/examples/server/tests/features/steps/steps.py
+++ b/examples/server/tests/features/steps/steps.py
@@ -88,7 +88,7 @@ def step_start_server(context):
         with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as sock:
             result = sock.connect_ex((context.server_fqdn, context.server_port))
             if result == 0:
-                print("\x1b[33;42mserver started!\x1b[0m")
+                print("\x1b[33;46mserver started!\x1b[0m")
                 return
             attempts += 1
             if attempts > 20: