test(harness): num_llm_calls is None (not 0) for no-usage default cases

TurnUsage.num_llm_calls is Optional on next (None = "not reported"). The
openai / pydantic-ai turn tests still asserted == 0 for the default (no-usage /
pre-exhaustion) path, which now yields None. Update those three assertions to
`is None`; real-zero cases are unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: declan-scale

tests/lib/adk/providers/test_openai_turn.py

@@ -65,7 +65,9 @@ def test_usage_mapping_none_usage():
     turn_usage = openai_usage_to_turn_usage(None, model="gpt-4o")
 
     assert turn_usage.model == "gpt-4o"
-    assert turn_usage.num_llm_calls == 0
+    # num_llm_calls is None ("not reported") when no usage is present, matching
+    # the token fields below; a real 0 is only reported when the provider says so.
+    assert turn_usage.num_llm_calls is None
     assert turn_usage.input_tokens is None
     assert turn_usage.output_tokens is None
     assert turn_usage.total_tokens is None

tests/lib/adk/test_pydantic_ai_turn.py

@@ -122,7 +122,7 @@ async def test_usage_before_exhaustion_returns_default(self):
         assert pre_usage.model == "openai:gpt-4o"
         assert pre_usage.input_tokens is None
         assert pre_usage.output_tokens is None
-        assert pre_usage.num_llm_calls == 0
+        assert pre_usage.num_llm_calls is None
 
     async def test_turn_events_and_usage(self):
         """Driving events to exhaustion populates usage from the terminal event."""
@@ -227,7 +227,7 @@ async def test_no_usage_event_leaves_default_usage(self):
         usage = turn.usage()
         assert usage.model == "openai:gpt-4o"
         assert usage.input_tokens is None
-        assert usage.num_llm_calls == 0
+        assert usage.num_llm_calls is None
 
 
 class TestToolRequestStreaming: