feat(langchain): Update LLM span operation to gen_ai.generate_text

Change LLM span operation type from gen_ai.pipeline to gen_ai.generate_text
and update span naming to include the model identifier.

- Use gen_ai.generate_text operation for LLM calls
- Set span name to 'generate_text {model}' instead of generic 'Langchain LLM call'
- Update test assertions to match new span operation and description

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

Author: ericapisani

sentry_sdk/integrations/langchain.py

@@ -351,7 +351,6 @@ def on_llm_start(
         metadata: "Optional[Dict[str, Any]]" = None,
         **kwargs: "Any",
     ) -> "Any":
-        """Run when LLM starts running."""
         with capture_internal_exceptions():
             if not run_id:
                 return
@@ -369,8 +368,8 @@ def on_llm_start(
             watched_span = self._create_span(
                 run_id,
                 parent_run_id,
-                op=OP.GEN_AI_PIPELINE,
-                name=kwargs.get("name") or "Langchain LLM call",
+                op=OP.GEN_AI_GENERATE_TEXT,
+                name=f"generate_text {model}".strip(),
                 origin=LangchainIntegration.origin,
             )
             span = watched_span.span

tests/integrations/langchain/test_langchain.py

@@ -851,12 +851,14 @@ def test_langchain_integration_with_langchain_core_only(sentry_init, capture_eve
         assert tx["type"] == "transaction"
 
         llm_spans = [
-            span for span in tx.get("spans", []) if span.get("op") == "gen_ai.pipeline"
+            span
+            for span in tx.get("spans", [])
+            if span.get("op") == "gen_ai.generate_text"
         ]
         assert len(llm_spans) > 0
 
         llm_span = llm_spans[0]
-        assert llm_span["description"] == "Langchain LLM call"
+        assert llm_span["description"] == "generate_text gpt-3.5-turbo"
         assert llm_span["data"]["gen_ai.request.model"] == "gpt-3.5-turbo"
         assert (
             llm_span["data"]["gen_ai.response.text"]
@@ -1062,7 +1064,7 @@ def test_langchain_message_truncation(sentry_init, capture_events):
     assert tx["type"] == "transaction"
 
     llm_spans = [
-        span for span in tx.get("spans", []) if span.get("op") == "gen_ai.pipeline"
+        span for span in tx.get("spans", []) if span.get("op") == "gen_ai.generate_text"
     ]
     assert len(llm_spans) > 0
 
@@ -1776,7 +1778,7 @@ def test_langchain_response_model_extraction(
     assert tx["type"] == "transaction"
 
     llm_spans = [
-        span for span in tx.get("spans", []) if span.get("op") == "gen_ai.pipeline"
+        span for span in tx.get("spans", []) if span.get("op") == "gen_ai.generate_text"
     ]
     assert len(llm_spans) > 0