refactor(telemetry): rename duration metrics to GenAI semconv operation names

Rename gen_ai.agent.invocation.duration to gen_ai.invoke_agent.duration and
gen_ai.tool.execution.duration to gen_ai.execute_tool.duration so the metric
names match the GenAI semantic-convention operation names (invoke_agent,
execute_tool) already used for the corresponding spans.

Co-authored-by: Max Ind <maxind@google.com>
PiperOrigin-RevId: 941394506

Author: RKest

src/google/adk/telemetry/_metrics.py

@@ -47,7 +47,7 @@
 )
 
 _agent_invocation_duration = meter.create_histogram(
-    "gen_ai.agent.invocation.duration",
+    "gen_ai.invoke_agent.duration",
     unit="s",
     description="Duration of agent invocations.",
     explicit_bucket_boundaries_advisory=[
@@ -72,7 +72,7 @@
     description="Duration of workflow invocations.",
 )
 _tool_execution_duration = meter.create_histogram(
-    "gen_ai.tool.execution.duration",
+    "gen_ai.execute_tool.duration",
     unit="s",
     description="Duration of tool executions.",
     explicit_bucket_boundaries_advisory=[

tests/unittests/telemetry/functional_node_test_cases.py

@@ -2581,13 +2581,13 @@
 
 # Expected metric points, grouped by metric name.
 EXPECTED_NODE_METRICS_V1: dict[str, frozenset[MetricPoint]] = {
-    "gen_ai.agent.invocation.duration": frozenset({
+    "gen_ai.invoke_agent.duration": frozenset({
         MetricPoint(
             attributes={"gen_ai.agent.name": AGENT_NAME},
             value=NON_DETERMINISTIC,
         ),
     }),
-    "gen_ai.tool.execution.duration": frozenset({
+    "gen_ai.execute_tool.duration": frozenset({
         MetricPoint(
             attributes={
                 "gen_ai.agent.name": AGENT_NAME,
@@ -2637,13 +2637,13 @@
 
 
 EXPECTED_NODE_METRICS_V2: dict[str, frozenset[MetricPoint]] = {
-    "gen_ai.agent.invocation.duration": frozenset({
+    "gen_ai.invoke_agent.duration": frozenset({
         MetricPoint(
             attributes={"gen_ai.agent.name": AGENT_NAME},
             value=NON_DETERMINISTIC,
         ),
     }),
-    "gen_ai.tool.execution.duration": frozenset({
+    "gen_ai.execute_tool.duration": frozenset({
         MetricPoint(
             attributes={
                 "gen_ai.agent.name": AGENT_NAME,

tests/unittests/telemetry/functional_test_cases.py

@@ -2275,13 +2275,13 @@
 
 # Expected metric points, grouped by metric name.
 EXPECTED_METRICS_V1: dict[str, frozenset[MetricPoint]] = {
-    "gen_ai.agent.invocation.duration": frozenset({
+    "gen_ai.invoke_agent.duration": frozenset({
         MetricPoint(
             attributes={"gen_ai.agent.name": AGENT_NAME},
             value=NON_DETERMINISTIC,
         ),
     }),
-    "gen_ai.tool.execution.duration": frozenset({
+    "gen_ai.execute_tool.duration": frozenset({
         MetricPoint(
             attributes={
                 "gen_ai.agent.name": AGENT_NAME,
@@ -2322,13 +2322,13 @@
 
 
 EXPECTED_METRICS_V2: dict[str, frozenset[MetricPoint]] = {
-    "gen_ai.agent.invocation.duration": frozenset({
+    "gen_ai.invoke_agent.duration": frozenset({
         MetricPoint(
             attributes={"gen_ai.agent.name": AGENT_NAME},
             value=NON_DETERMINISTIC,
         ),
     }),
-    "gen_ai.tool.execution.duration": frozenset({
+    "gen_ai.execute_tool.duration": frozenset({
         MetricPoint(
             attributes={
                 "gen_ai.agent.name": AGENT_NAME,

tests/unittests/telemetry/functional_test_helpers.py

@@ -307,12 +307,12 @@ class HistogramSpec(NamedTuple):
     HistogramSpec(
         module=_metrics,
         attr="_agent_invocation_duration",
-        metric_name="gen_ai.agent.invocation.duration",
+        metric_name="gen_ai.invoke_agent.duration",
     ),
     HistogramSpec(
         module=_metrics,
         attr="_tool_execution_duration",
-        metric_name="gen_ai.tool.execution.duration",
+        metric_name="gen_ai.execute_tool.duration",
     ),
     HistogramSpec(
         module=_metrics,

tests/unittests/telemetry/test_metrics.py

@@ -45,11 +45,11 @@ def _mock_meter_setup(monkeypatch):
   client_token_usage_hist.name = "client_token_usage"
 
   def create_histogram_side_effect(name, **_kwargs):
-    if name == "gen_ai.agent.invocation.duration":
+    if name == "gen_ai.invoke_agent.duration":
       return agent_duration_hist
     elif name == "gen_ai.invoke_workflow.duration":
       return workflow_duration_hist
-    elif name == "gen_ai.tool.execution.duration":
+    elif name == "gen_ai.execute_tool.duration":
       return tool_duration_hist
     elif name == "gen_ai.agent.request.size":
       return request_size_hist