fix(live): propagate output token count in live API usage metadata

Merge #6064

**Please ensure you have read the [contribution guide](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) before creating a pull request.**

### Link to Issue or Description of Change

**Problem:**
Live API output token count in `usage_metadata` is always `0` (input/total are correct), so everything reading `candidates_token_count`reports zero output tokens for live sessions.

Root cause: live usage is a `types.UsageMetadata` (`response_token_count` / `response_tokens_details`), but `LlmResponse.usage_metadata` is a `types.GenerateContentResponseUsageMetadata` (`candidates_token_count` / `candidates_tokens_details`). The raw object was assigned directly; Pydantic re-validated into the target type and silently dropped the two renamed fields.

**Solution:**
Remap the live usage into `GenerateContentResponseUsageMetadata` in `gemini_llm_connection.receive()` via a `_to_generate_content_usage_metadata()` helper. Updated related tests.

### Testing Plan

**Unit Tests:**

- [X] I have added or updated unit tests for my change.
- [X] All unit tests pass locally.

$ uv run pytest tests/unittests/models/test_gemini_llm_connection.py -q
45 passed, 17 warnings in 1.25s

**Manual End-to-End (E2E) Tests:**

`uv run adk web contributing/samples/live --log_level DEBUG` → `live_bidi_streaming_single_agent`, audio stream. Confirmed live response's `usage_metadata.candidates_token_count` is now non-zero (was `0`), input/total unchanged.

### Checklist

- [X] I have read the [CONTRIBUTING.md](https://github.com/google/adk-python/blob/main/CONTRIBUTING.md) document.
- [X] I have performed a self-review of my own code.
- [X] I have commented my code, particularly in hard-to-understand areas.
- [X] I have added tests that prove my fix is effective or that my feature works.
- [X] New and existing unit tests pass locally with my changes.
- [X] I have manually tested my changes end-to-end.
- [X] Any dependent changes have been merged and published in downstream modules.

### Additional context

N/A

COPYBARA_INTEGRATE_REVIEW=#6064 from allen-stephen:fix/live-output-tokens 7ae8c29
PiperOrigin-RevId: 930500943

Author: allen-stephen

src/google/adk/models/gemini_llm_connection.py

@@ -216,6 +216,35 @@ def __build_full_text_response(
         live_session_id=self._gemini_session.session_id,
     )
 
+  def _to_generate_content_usage_metadata(
+      self, usage_metadata: types.UsageMetadata
+  ) -> types.GenerateContentResponseUsageMetadata:
+    """Converts live API usage metadata to GenerateContentResponse usage metadata.
+
+    The live API names output tokens `response_token_count`/
+    `response_tokens_details`, whereas `GenerateContentResponseUsageMetadata`
+    names them `candidates_token_count`/`candidates_tokens_details`.
+
+    Args:
+      usage_metadata: The live API usage metadata.
+
+    Returns:
+      The converted usage metadata.
+    """
+    return types.GenerateContentResponseUsageMetadata(
+        prompt_token_count=usage_metadata.prompt_token_count,
+        cached_content_token_count=usage_metadata.cached_content_token_count,
+        candidates_token_count=usage_metadata.response_token_count,
+        total_token_count=usage_metadata.total_token_count,
+        thoughts_token_count=usage_metadata.thoughts_token_count,
+        tool_use_prompt_token_count=usage_metadata.tool_use_prompt_token_count,
+        prompt_tokens_details=usage_metadata.prompt_tokens_details,
+        cache_tokens_details=usage_metadata.cache_tokens_details,
+        candidates_tokens_details=usage_metadata.response_tokens_details,
+        tool_use_prompt_tokens_details=usage_metadata.tool_use_prompt_tokens_details,
+        traffic_type=usage_metadata.traffic_type,
+    )
+
   async def receive(self) -> AsyncGenerator[LlmResponse, None]:
     """Receives the model response using the llm server connection.
 
@@ -234,9 +263,11 @@ async def receive(self) -> AsyncGenerator[LlmResponse, None]:
         logger.debug('Got LLM Live message: %s', message)
         live_session_id = self._gemini_session.session_id
         if message.usage_metadata:
-          # Tracks token usage data per model.
+          # Remap live token usage to GenerateContentResponse usage metadata.
           yield LlmResponse(
-              usage_metadata=message.usage_metadata,
+              usage_metadata=self._to_generate_content_usage_metadata(
+                  message.usage_metadata
+              ),
               model_version=self._model_version,
               live_session_id=live_session_id,
           )

tests/unittests/models/test_gemini_llm_connection.py

@@ -231,10 +231,12 @@ async def mock_receive_generator():
   content_response = next((r for r in responses if r.content), None)
   assert content_response is not None
 
+  # The live API's `response_token_count`/`response_tokens_details` are remapped
+  # to `candidates_token_count`/`candidates_tokens_details`.
   expected_usage = types.GenerateContentResponseUsageMetadata(
       prompt_token_count=10,
       cached_content_token_count=5,
-      candidates_token_count=None,
+      candidates_token_count=20,
       total_token_count=35,
       thoughts_token_count=2,
       prompt_tokens_details=[
@@ -243,12 +245,74 @@ async def mock_receive_generator():
       cache_tokens_details=[
           types.ModalityTokenCount(modality='text', token_count=5)
       ],
-      candidates_tokens_details=None,
+      candidates_tokens_details=[
+          types.ModalityTokenCount(modality='text', token_count=20)
+      ],
   )
   assert usage_response.usage_metadata == expected_usage
   assert content_response.content == mock_content
 
 
+async def test_receive_usage_metadata_remaps_output_tokens(
+    gemini_connection, mock_gemini_session
+):
+  """Test that live API output tokens are remapped to candidates_token_count."""
+  usage_metadata = types.UsageMetadata(
+      prompt_token_count=10,
+      cached_content_token_count=5,
+      response_token_count=20,
+      total_token_count=35,
+      thoughts_token_count=2,
+      tool_use_prompt_token_count=3,
+      prompt_tokens_details=[
+          types.ModalityTokenCount(modality='text', token_count=10)
+      ],
+      cache_tokens_details=[
+          types.ModalityTokenCount(modality='text', token_count=5)
+      ],
+      response_tokens_details=[
+          types.ModalityTokenCount(modality='text', token_count=20)
+      ],
+  )
+
+  mock_message = mock.AsyncMock()
+  mock_message.usage_metadata = usage_metadata
+  mock_message.server_content = None
+  mock_message.tool_call = None
+  mock_message.session_resumption_update = None
+  mock_message.go_away = None
+
+  async def mock_receive_generator():
+    yield mock_message
+
+  receive_mock = mock.Mock(return_value=mock_receive_generator())
+  mock_gemini_session.receive = receive_mock
+
+  responses = [resp async for resp in gemini_connection.receive()]
+
+  usage_response = next((r for r in responses if r.usage_metadata), None)
+  assert usage_response is not None
+  result = usage_response.usage_metadata
+  assert isinstance(result, types.GenerateContentResponseUsageMetadata)
+  # Output tokens are remapped from response_* to candidates_*.
+  assert result.candidates_token_count == 20
+  assert result.candidates_tokens_details == [
+      types.ModalityTokenCount(modality='text', token_count=20)
+  ]
+  # Shared fields are carried over unchanged.
+  assert result.prompt_token_count == 10
+  assert result.cached_content_token_count == 5
+  assert result.total_token_count == 35
+  assert result.thoughts_token_count == 2
+  assert result.tool_use_prompt_token_count == 3
+  assert result.prompt_tokens_details == [
+      types.ModalityTokenCount(modality='text', token_count=10)
+  ]
+  assert result.cache_tokens_details == [
+      types.ModalityTokenCount(modality='text', token_count=5)
+  ]
+
+
 async def test_receive_populates_live_session_id(
     gemini_connection, mock_gemini_session
 ):