fix(a2a): populate response usage in a2a chat transformation

litellm/llms/a2a/chat/transformation.py

@@ -10,7 +10,7 @@
 from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator
 from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException
 from litellm.types.llms.openai import AllMessageValues
-from litellm.types.utils import Choices, Message, ModelResponse
+from litellm.types.utils import Choices, Message, ModelResponse, Usage
 
 from ..common_utils import (
     A2AError,
@@ -312,6 +312,25 @@ def transform_response(
         # Set ID from response
         model_response.id = response_json.get("id", str(uuid.uuid4()))
 
+        # A2A agents don't return token usage; estimate it so per-token pricing
+        # produces real cost and callers don't receive usage of 0/0/0.
+        try:
+            from litellm.utils import token_counter
+
+            prompt_tokens = token_counter(model="gpt-3.5-turbo", messages=messages)
+            completion_tokens = token_counter(model="gpt-3.5-turbo", text=text, count_response_tokens=True)
+            setattr(
+                model_response,
+                "usage",
+                Usage(
+                    prompt_tokens=prompt_tokens,
+                    completion_tokens=completion_tokens,
+                    total_tokens=prompt_tokens + completion_tokens,
+                ),
+            )
+        except Exception:  # noqa: BLE001 - best-effort estimate; a tokenizer hiccup must not break the response
+            pass
+
         return model_response
 
     def get_model_response_iterator(

tests/test_litellm/llms/a2a/chat/test_a2a_chat_transformation.py

@@ -0,0 +1,42 @@
+"""Tests for litellm/llms/a2a/chat/transformation.py response transform."""
+
+from unittest.mock import MagicMock
+
+from litellm.llms.a2a.chat.transformation import A2AConfig
+from litellm.types.utils import ModelResponse
+
+
+def _raw_response(text: str) -> MagicMock:
+    raw = MagicMock()
+    raw.status_code = 200
+    raw.headers = {}
+    raw.json.return_value = {
+        "jsonrpc": "2.0",
+        "id": "resp-1",
+        "result": {
+            "kind": "message",
+            "parts": [{"kind": "text", "text": text}],
+        },
+    }
+    return raw
+
+
+def test_transform_response_sets_usage():
+    """Regression: A2AConfig.transform_response must populate usage so per-token
+    pricing computes real cost and callers don't get usage 0/0/0."""
+    result = A2AConfig().transform_response(
+        model="a2a/test-agent",
+        raw_response=_raw_response("hello from the agent"),
+        model_response=ModelResponse(),
+        logging_obj=MagicMock(),
+        request_data={},
+        messages=[{"role": "user", "content": "hi there agent"}],
+        optional_params={},
+        litellm_params={},
+        encoding=None,
+    )
+
+    assert result.usage is not None
+    assert result.usage.prompt_tokens > 0
+    assert result.usage.completion_tokens > 0
+    assert result.usage.total_tokens == (result.usage.prompt_tokens + result.usage.completion_tokens)