fix(utils.py): fix setattr error

.pre-commit-config.yaml

@@ -16,11 +16,11 @@ repos:
         name: Check if files match
         entry: python3 ci_cd/check_files_match.py
         language: system
-# -   repo: local
+-   repo: local
-#     hooks:
+    hooks:
-#     -   id: mypy
+    -   id: mypy
-#         name: mypy
+        name: mypy
-#         entry: python3 -m mypy --ignore-missing-imports
+        entry: python3 -m mypy --ignore-missing-imports
-#         language: system
+        language: system
-#         types: [python]
+        types: [python]
-#         files: ^litellm/
+        files: ^litellm/

litellm/proxy/_super_secret_config.yaml

@@ -0,0 +1,48 @@
+environment_variables:
+  SLACK_WEBHOOK_URL: SQD2/FQHvDuj6Q9/Umyqi+EKLNKKLRCXETX2ncO0xCIQp6EHCKiYD7jPW0+1QdrsQ+pnEzhsfVY2r21SiQV901n/9iyJ2tSnEyWViP7FKQVtTvwutsAqSqbiVHxLHbpjPCu03fhS/idjZrtK7dJLbLBB3RgudjNjHg==
+general_settings:
+  alerting:
+  - slack
+  alerting_threshold: 300
+  database_connection_pool_limit: 100
+  database_connection_timeout: 60
+  health_check_interval: 300
+  proxy_batch_write_at: 10
+  ui_access_mode: all
+litellm_settings:
+  allowed_fails: 3
+  failure_callback:
+  - prometheus
+  fallbacks:
+  - gpt-3.5-turbo:
+    - fake-openai-endpoint
+    - gpt-4
+  num_retries: 3
+  service_callback:
+  - prometheus_system
+  success_callback:
+  - prometheus
+model_list:
+- litellm_params:
+    api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/
+    api_key: my-fake-key
+    model: openai/my-fake-model
+  model_name: fake-openai-endpoint
+- litellm_params:
+    model: gpt-3.5-turbo
+  model_name: gpt-3.5-turbo
+router_settings:
+  allowed_fails: 3
+  context_window_fallbacks: null
+  cooldown_time: 1
+  fallbacks:
+  - gpt-3.5-turbo:
+    - fake-openai-endpoint
+    - gpt-4
+  - gpt-3.5-turbo-3:
+    - fake-openai-endpoint
+  num_retries: 3
+  retry_after: 0
+  routing_strategy: simple-shuffle
+  routing_strategy_args: {}
+  timeout: 6000

litellm/utils.py

@@ -6914,6 +6914,7 @@ def convert_to_streaming_response(response_object: Optional[dict] = None):
     model_response_object.choices = choice_list
 
     if "usage" in response_object and response_object["usage"] is not None:
+        setattr(model_response_object, "usage", Usage())
         model_response_object.usage.completion_tokens = response_object["usage"].get("completion_tokens", 0)  # type: ignore
         model_response_object.usage.prompt_tokens = response_object["usage"].get("prompt_tokens", 0)  # type: ignore
         model_response_object.usage.total_tokens = response_object["usage"].get("total_tokens", 0)  # type: ignore