feat(litellm_logging.py): log exception response headers to langfuse

litellm/integrations/langfuse.py

@@ -5,6 +5,7 @@ import os
 import traceback
 
 from packaging.version import Version
+from pydantic import BaseModel
 
 import litellm
 from litellm._logging import verbose_logger
@@ -43,8 +44,8 @@ class LangFuseLogger:
         self.langfuse_debug = os.getenv("LANGFUSE_DEBUG")
 
         parameters = {
-            "public_key": self.public_key,
-            "secret_key": self.secret_key,
+            "public_key": "pk-lf-b3db7e8e-c2f6-4fc7-825c-a541a8fbe003",
+            "secret_key": "sk-lf-b11ef3a8-361c-4445-9652-12318b8596e4",
             "host": self.langfuse_host,
             "release": self.langfuse_release,
             "debug": self.langfuse_debug,
@@ -331,7 +332,7 @@ class LangFuseLogger:
                 metadata = copy.deepcopy(
                     metadata
                 )  # Avoid modifying the original metadata
-            except:
+            except Exception:
                 new_metadata = {}
                 for key, value in metadata.items():
                     if (
@@ -342,6 +343,8 @@ class LangFuseLogger:
                         or isinstance(value, float)
                     ):
                         new_metadata[key] = copy.deepcopy(value)
+                    elif isinstance(value, BaseModel):
+                        new_metadata[key] = value.model_dump()
                 metadata = new_metadata
 
             supports_tags = Version(langfuse.version.__version__) >= Version("2.6.3")

litellm/litellm_core_utils/litellm_logging.py

@@ -1543,6 +1543,13 @@ class Logging:
         self.model_call_details["end_time"] = end_time
         self.model_call_details.setdefault("original_response", None)
         self.model_call_details["response_cost"] = 0
+
+        if hasattr(exception, "headers") and isinstance(exception.headers, dict):
+            self.model_call_details.setdefault("litellm_params", {})
+            metadata = (
+                self.model_call_details["litellm_params"].get("metadata", {}) or {}
+            )
+            metadata.update(exception.headers)
         return start_time, end_time
 
     def failure_handler(

litellm/proxy/_new_secret_config.yaml

@@ -1,11 +1,8 @@
 model_list:
-  - model_name: "*"
+  - model_name: "predibase-llama"
     litellm_params:
-      model: "*"
-  - model_name: "azure-gpt-4o-mini"
-    litellm_params:
-      model: azure/my-gpt-4o-mini
-      api_key: os.environ/AZURE_API_KEY
-      api_base: os.environ/AZURE_API_BASE
-    model_info:
-      base_model: azure/global-standard/gpt-4o-mini
+      model: "predibase/llama-3-8b-instruct"
+      request_timeout: 1
+
+litellm_settings:
+  failure_callback: ["langfuse"]