[BREAKING] Python: Consolidate OTel GenAI Semantic Conventions versions

python/packages/ag-ui/tests/ag_ui/test_endpoint.py

@@ -5472,7 +5472,11 @@ async def test_agent_endpoint_correlates_gen_ai_spans_with_supplied_thread_id(
     monkeypatch.setattr(
         observability,
         "OBSERVABILITY_SETTINGS",
-        SimpleNamespace(ENABLED=True, SENSITIVE_DATA_ENABLED=False),
+        SimpleNamespace(
+            ENABLED=True,
+            SENSITIVE_DATA_ENABLED=False,
+            use_latest_experimental_gen_ai_semconv=True,
+        ),
     )
     monkeypatch.setattr(observability, "get_tracer", lambda *args, **kwargs: tracer_provider.get_tracer("test"))
 

python/packages/ag-ui/tests/ag_ui/test_workflow_run.py

@@ -133,7 +133,11 @@ async def test_workflow_and_agent_spans_use_supplied_agui_thread_id(monkeypatch:
     monkeypatch.setattr(
         observability,
         "OBSERVABILITY_SETTINGS",
-        SimpleNamespace(ENABLED=True, SENSITIVE_DATA_ENABLED=False),
+        SimpleNamespace(
+            ENABLED=True,
+            SENSITIVE_DATA_ENABLED=False,
+            use_latest_experimental_gen_ai_semconv=True,
+        ),
     )
     monkeypatch.setattr(observability, "get_tracer", lambda *args, **kwargs: tracer_provider.get_tracer("test"))
 

python/packages/core/agent_framework/_sessions.py

@@ -35,7 +35,7 @@
 from dataclasses import dataclass
 from functools import partial
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypeAlias, TypeVar, cast, TypeGuard
+from typing import TYPE_CHECKING, Any, ClassVar, Literal, TypeAlias, TypeVar, cast
 
 import msgspec
 
@@ -251,6 +251,7 @@ class _StateTypeRegistration:
     encoder: StateEncoder
     decoder: StateDecoder
 
+
 _STATE_TYPE_REGISTRY: dict[str, _StateTypeRegistration] = {}
 _STATE_CLASS_REGISTRY: dict[type[Any], _StateTypeRegistration] = {}
 

python/packages/core/agent_framework/_tools.py

@@ -746,7 +746,10 @@ async def invoke(
                 "response_format",
             }
         }
-        if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED:
+        # gen_ai.tool.call.arguments/result were introduced above v1.36.0; only emit them
+        # as span attributes when that semconv version is active.
+        emit_tool_call_attrs = OBSERVABILITY_SETTINGS.emit_tool_call_attributes
+        if emit_tool_call_attrs:
             attributes.update({
                 OtelAttr.TOOL_ARGUMENTS: (
                     json.dumps(serializable_kwargs, default=str, ensure_ascii=False) if serializable_kwargs else "None"
@@ -773,8 +776,9 @@ async def invoke(
                     logger.info(f"Function {self.name} succeeded.")
                     if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED:
                         result_str = str(result)
-                        span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
                         logger.debug(f"Function result: {result_str}")
+                        if emit_tool_call_attrs:
+                            span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
                     return result
                 try:
                     parsed = parser(result)
@@ -786,8 +790,9 @@ async def invoke(
                 logger.info(f"Function {self.name} succeeded.")
                 if OBSERVABILITY_SETTINGS.SENSITIVE_DATA_ENABLED:
                     result_str = "\n".join(c.text or "" for c in parsed if c.type == "text") or str(parsed)
-                    span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
                     logger.debug(f"Function result: {result_str}")
+                    if emit_tool_call_attrs:
+                        span.set_attribute(OtelAttr.TOOL_RESULT, result_str)
                 return parsed
             finally:
                 duration = (end_time_stamp or perf_counter()) - start_time_stamp

python/packages/core/tests/conftest.py

@@ -4,6 +4,9 @@
 from typing import Any
 from unittest.mock import patch
 
+from opentelemetry._logs import get_logger_provider, set_logger_provider
+from opentelemetry.sdk._logs import LoggerProvider
+from opentelemetry.sdk._logs.export import InMemoryLogRecordExporter, SimpleLogRecordProcessor
 from opentelemetry.sdk.trace.export import SimpleSpanProcessor, SpanExporter
 from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
 from pytest import fixture
@@ -29,6 +32,8 @@ def span_exporter(monkeypatch, enable_instrumentation: bool, enable_sensitive_da
         "ENABLE_INSTRUMENTATION",
         "ENABLE_SENSITIVE_DATA",
         "ENABLE_CONSOLE_EXPORTERS",
+        "ENABLE_MESSAGE_EVENTS",
+        "OTEL_SEMCONV_STABILITY_OPT_IN",
         "OTEL_EXPORTER_OTLP_ENDPOINT",
         "OTEL_EXPORTER_OTLP_TRACES_ENDPOINT",
         "OTEL_EXPORTER_OTLP_METRICS_ENDPOINT",
@@ -87,3 +92,23 @@ def span_exporter(monkeypatch, enable_instrumentation: bool, enable_sensitive_da
         yield exporter
         # Clean up
         exporter.clear()
+
+
+@fixture
+def log_record_exporter(span_exporter: SpanExporter) -> Generator[InMemoryLogRecordExporter]:
+    """Fixture providing an in-memory exporter for OTel log records (e.g. gen_ai message events).
+
+    Depends on ``span_exporter`` so ObservabilitySettings/env vars are configured first. The global
+    OTel LoggerProvider can only be set once per process, so on later test runs this just attaches
+    another processor to whichever LoggerProvider a previous test already installed.
+    """
+    exporter = InMemoryLogRecordExporter()
+    set_logger_provider(LoggerProvider())
+    provider = get_logger_provider()
+    if not hasattr(provider, "add_log_record_processor"):
+        raise RuntimeError("Logger provider does not support adding log record processors.")
+    provider.add_log_record_processor(SimpleLogRecordProcessor(exporter))  # type: ignore
+
+    yield exporter
+    # Clean up
+    exporter.clear()