Switch tests and samples to gpt-4.1 and refresh VCR cassettes

Author: nagkumar91

instrumentation-genai/opentelemetry-instrumentation-langchain/examples/multi_agent_travel_planner/.env.sample

@@ -3,8 +3,8 @@
 # Required OpenAI API key
 OPENAI_API_KEY=sk-YOUR_API_KEY
 
-# Optional: override default model (defaults to gpt-4o-mini)
-# OPENAI_MODEL=gpt-4o-mini
+# Optional: override default model (defaults to gpt-4.1)
+# OPENAI_MODEL=gpt-4.1
 
 # OTLP exporter configuration (update for your collector)
 # OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

instrumentation-genai/opentelemetry-instrumentation-langchain/examples/multi_agent_travel_planner/main.py

@@ -184,7 +184,7 @@ class PlannerState(TypedDict):
 
 
 def _model_name() -> str:
-    return os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    return os.getenv("OPENAI_MODEL", "gpt-4.1")
 
 
 def _create_llm(

instrumentation-genai/opentelemetry-instrumentation-langchain/tests/cassettes/test_chat_openai_gpt_3_5_turbo_model_llm_call.yaml renamed to instrumentation-genai/opentelemetry-instrumentation-langchain/tests/cassettes/test_chat_openai_gpt_4_1_model_llm_call.yaml

@@ -12,7 +12,7 @@ interactions:
             "role": "user"
           }
         ],
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-4.1",
         "frequency_penalty": 0.5,
         "max_completion_tokens": 100,
         "presence_penalty": 0.5,
@@ -36,13 +36,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '316'
+      - '310'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.106.1
+      - OpenAI/Python 1.109.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -52,25 +52,25 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.106.1
+      - 1.109.1
       x-stainless-raw-response:
       - 'true'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.13.5
+      - 3.11.14
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
       string: |-
         {
-          "id": "chatcmpl-CCAQbtjsmG2294sQ6utRc16OQWeol",
+          "id": "chatcmpl-CTB9d2RMw2N2EBwVMAnYR45AvBvud",
           "object": "chat.completion",
-          "created": 1757016057,
-          "model": "gpt-3.5-turbo-0125",
+          "created": 1761070425,
+          "model": "gpt-4.1-2025-04-14",
           "choices": [
             {
               "index": 0,
@@ -100,17 +100,17 @@ interactions:
             }
           },
           "service_tier": "default",
-          "system_fingerprint": null
+          "system_fingerprint": "fp_e24a1fec47"
         }
     headers:
       CF-RAY:
-      - 97a01376ad4d2af1-LAX
+      - 9922bb0f79e7a9f8-SEA
       Connection:
       - keep-alive
       Content-Type:
       - application/json
       Date:
-      - Thu, 04 Sep 2025 20:00:57 GMT
+      - Tue, 21 Oct 2025 18:13:46 GMT
       Server:
       - cloudflare
       Set-Cookie: test_set_cookie
@@ -127,30 +127,32 @@ interactions:
       cf-cache-status:
       - DYNAMIC
       content-length:
-      - '822'
+      - '833'
       openai-organization: test_openai_org_id
       openai-processing-ms:
-      - '282'
+      - '353'
       openai-project:
-      - proj_GLiYlAc06hF0Fm06IMReZLy4
+      - proj_g22EI7wYA0CcaIteeCvlmSng
       openai-version:
       - '2020-10-01'
       x-envoy-upstream-service-time:
-      - '287'
+      - '514'
+      x-openai-proxy-wasm:
+      - v0.1
       x-ratelimit-limit-requests:
-      - '10000'
+      - '500'
       x-ratelimit-limit-tokens:
-      - '200000'
+      - '30000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '499'
       x-ratelimit-remaining-tokens:
-      - '199982'
+      - '29982'
       x-ratelimit-reset-requests:
-      - 8.64s
+      - 120ms
       x-ratelimit-reset-tokens:
-      - 5ms
+      - 36ms
       x-request-id:
-      - req_0e343602788d4f33869d09afcc7d4819
+      - req_e6d40dc7ffc44d3e929f2883bdd89612
     status:
       code: 200
       message: OK

instrumentation-genai/opentelemetry-instrumentation-langchain/tests/cassettes/test_us_amazon_nova_lite_v1_0_bedrock_llm_call.yaml

@@ -46,7 +46,7 @@ interactions:
       authorization:
       - Bearer test_openai_api_key
     method: POST
-    uri: https://bedrock-runtime.us-west-2.amazonaws.com/model/arn%3Aaws%3Abedrock%3Aus-west-2%3A906383545488%3Ainference-profile%2Fus.amazon.nova-lite-v1%3A0/converse
+    uri: https://bedrock-runtime.us-west-2.amazonaws.com/model/us.amazon.nova-lite-v1%3A0/converse
   response:
     body:
       string: |-

instrumentation-genai/opentelemetry-instrumentation-langchain/tests/conftest.py

@@ -19,10 +19,10 @@
 )
 
 
-@pytest.fixture(scope="function", name="chat_openai_gpt_3_5_turbo_model")
-def fixture_chat_openai_gpt_3_5_turbo_model():
+@pytest.fixture(scope="function", name="chat_openai_gpt_4_1_model")
+def fixture_chat_openai_gpt_4_1_model():
     llm = ChatOpenAI(
-        model="gpt-3.5-turbo",
+        model="gpt-4.1",
         temperature=0.1,
         max_tokens=100,
         top_p=0.9,

instrumentation-genai/opentelemetry-instrumentation-langchain/tests/test_llm_call.py

@@ -21,17 +21,17 @@
 )
 
 
-# span_exporter, start_instrumentation, chat_openai_gpt_3_5_turbo_model are coming from fixtures defined in conftest.py
+# span_exporter, start_instrumentation, chat_openai_gpt_4_1_model are coming from fixtures defined in conftest.py
 @pytest.mark.vcr()
-def test_chat_openai_gpt_3_5_turbo_model_llm_call(
-    span_exporter, start_instrumentation, chat_openai_gpt_3_5_turbo_model
+def test_chat_openai_gpt_4_1_model_llm_call(
+    span_exporter, start_instrumentation, chat_openai_gpt_4_1_model
 ):
     messages = [
         SystemMessage(content="You are a helpful assistant!"),
         HumanMessage(content="What is the capital of France?"),
     ]
 
-    response = chat_openai_gpt_3_5_turbo_model.invoke(messages)
+    response = chat_openai_gpt_4_1_model.invoke(messages)
     assert response.content == "The capital of France is Paris."
 
     # verify spans
@@ -87,15 +87,12 @@ def test_gemini(span_exporter, start_instrumentation, gemini):
 def assert_openai_completion_attributes(
     span: ReadableSpan, response: Optional
 ):
-    assert span.name == "chat gpt-3.5-turbo"
+    assert span.name == "chat gpt-4.1"
     assert span.attributes[gen_ai_attributes.GEN_AI_OPERATION_NAME] == "chat"
-    assert (
-        span.attributes[gen_ai_attributes.GEN_AI_REQUEST_MODEL]
-        == "gpt-3.5-turbo"
-    )
+    assert span.attributes[gen_ai_attributes.GEN_AI_REQUEST_MODEL] == "gpt-4.1"
     assert (
         span.attributes[gen_ai_attributes.GEN_AI_RESPONSE_MODEL]
-        == "gpt-3.5-turbo-0125"
+        == "gpt-4.1-2025-04-14"
     )
     assert span.attributes[gen_ai_attributes.GEN_AI_REQUEST_MAX_TOKENS] == 100
     assert span.attributes[gen_ai_attributes.GEN_AI_REQUEST_TEMPERATURE] == 0.1