feat: show token usage per assistant response (#2270)

* feat: show token usage per assistant response

* fix: align client models response with token usage

* fix: address token usage review feedback

* docs: clarify token usage config example

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/app/gateway/routers/models.py

@@ -17,10 +17,17 @@ class ModelResponse(BaseModel):
     supports_reasoning_effort: bool = Field(default=False, description="Whether model supports reasoning effort")
 
 
+class TokenUsageResponse(BaseModel):
+    """Token usage display configuration."""
+
+    enabled: bool = Field(default=False, description="Whether token usage display is enabled")
+
+
 class ModelsListResponse(BaseModel):
     """Response model for listing all models."""
 
     models: list[ModelResponse]
+    token_usage: TokenUsageResponse
 
 
 @router.get(
@@ -36,7 +43,7 @@ async def list_models() -> ModelsListResponse:
     excluding sensitive fields like API keys and internal configuration.
 
     Returns:
-        A list of all configured models with their metadata.
+        A list of all configured models with their metadata and token usage display settings.
 
     Example Response:
         ```json
@@ -44,17 +51,24 @@ async def list_models() -> ModelsListResponse:
             "models": [
                 {
                     "name": "gpt-4",
+                    "model": "gpt-4",
                     "display_name": "GPT-4",
                     "description": "OpenAI GPT-4 model",
-                    "supports_thinking": false
+                    "supports_thinking": false,
+                    "supports_reasoning_effort": false
                 },
                 {
                     "name": "claude-3-opus",
+                    "model": "claude-3-opus",
                     "display_name": "Claude 3 Opus",
                     "description": "Anthropic Claude 3 Opus model",
-                    "supports_thinking": true
+                    "supports_thinking": true,
+                    "supports_reasoning_effort": false
                 }
-            ]
+            ],
+            "token_usage": {
+                "enabled": true
+            }
         }
         ```
     """
@@ -70,7 +84,10 @@ async def list_models() -> ModelsListResponse:
         )
         for model in config.models
     ]
-    return ModelsListResponse(models=models)
+    return ModelsListResponse(
+        models=models,
+        token_usage=TokenUsageResponse(enabled=config.token_usage.enabled),
+    )
 
 
 @router.get(

backend/packages/harness/deerflow/client.py

@@ -722,6 +722,10 @@ class DeerFlowClient:
             Dict with "models" key containing list of model info dicts,
             matching the Gateway API ``ModelsListResponse`` schema.
         """
+        token_usage_enabled = getattr(getattr(self._app_config, "token_usage", None), "enabled", False)
+        if not isinstance(token_usage_enabled, bool):
+            token_usage_enabled = False
+
         return {
             "models": [
                 {
@@ -733,7 +737,8 @@ class DeerFlowClient:
                     "supports_reasoning_effort": getattr(model, "supports_reasoning_effort", False),
                 }
                 for model in self._app_config.models
-            ]
+            ],
+            "token_usage": {"enabled": token_usage_enabled},
         }
 
     def list_skills(self, enabled_only: bool = False) -> dict:

backend/tests/test_client.py

@@ -38,6 +38,7 @@ def mock_app_config():
 
     config = MagicMock()
     config.models = [model]
+    config.token_usage.enabled = False
     return config
 
 
@@ -107,6 +108,7 @@ class TestConfigQueries:
     def test_list_models(self, client):
         result = client.list_models()
         assert "models" in result
+        assert result["token_usage"] == {"enabled": False}
         assert len(result["models"]) == 1
         assert result["models"][0]["name"] == "test-model"
         # Verify Gateway-aligned fields are present
@@ -2196,7 +2198,9 @@ class TestGatewayConformance:
         model.display_name = "Test Model"
         model.description = "A test model"
         model.supports_thinking = False
+        model.supports_reasoning_effort = False
         mock_app_config.models = [model]
+        mock_app_config.token_usage.enabled = True
 
         with patch("deerflow.client.get_app_config", return_value=mock_app_config):
             client = DeerFlowClient()
@@ -2206,6 +2210,7 @@ class TestGatewayConformance:
         assert len(parsed.models) == 1
         assert parsed.models[0].name == "test-model"
         assert parsed.models[0].model == "gpt-test"
+        assert parsed.token_usage.enabled is True
 
     def test_get_model(self, mock_app_config):
         model = MagicMock()