feat(types): add EvalVerdict, StandardLoggingEvalInformation; wire eval_information into SpendLogsMetadata

litellm/proxy/_types.py

@@ -3332,6 +3332,7 @@ class SpendLogsMetadata(TypedDict):
     mcp_tool_call_metadata: Optional[StandardLoggingMCPToolCall]
     vector_store_request_metadata: Optional[List[StandardLoggingVectorStoreRequest]]
     guardrail_information: Optional[List[StandardLoggingGuardrailInformation]]
+    eval_information: Optional[Any]
     status: StandardLoggingPayloadStatus
     proxy_server_request: Optional[str]
     batch_models: Optional[List[str]]

litellm/proxy/spend_tracking/spend_tracking_utils.py

@@ -107,6 +107,7 @@ def _get_spend_logs_metadata(
             model_map_information=None,
             usage_object=None,
             guardrail_information=None,
+            eval_information=None,
             cold_storage_object_key=cold_storage_object_key,
             litellm_overhead_time_ms=None,
             attempted_retries=None,

litellm/types/utils.py

@@ -2760,6 +2760,29 @@ class StandardLoggingGuardrailInformation(TypedDict, total=False):
     """Risk score 0-10 indicating how risky the request was (higher = riskier). Computed by the guardrail provider."""
 
 
+class EvalVerdict(TypedDict, total=False):
+    criterion_name: str
+    score: float  # 0-100
+    reasoning: str
+    passed: bool
+    weight: int  # criterion weight (0-100) as configured in the guardrail
+
+
+class StandardLoggingEvalInformation(TypedDict, total=False):
+    eval_id: Optional[str]
+    eval_name: str
+    overall_score: float
+    passed: bool
+    judge_model: str
+    iteration: int
+    eval_error: Optional[str]
+    start_time: str
+    end_time: str
+    duration: float
+    verdicts: List[Any]
+    threshold: Optional[float]
+
+
 class GuardrailTracingDetail(TypedDict, total=False):
     """
     Typed fields for guardrail tracing metadata.