What happened?
I am deploying LiteLLM Proxy on Kubernetes and using ArgoCD for synchronization. The application is running, and both readiness and liveness probes return 200 OK, but the logs are continuously filled with the following error:
INFO: 10.116.161.254:36682 - "GET /health/liveliness HTTP/1.1" 200 OK
INFO: 10.116.161.254:36690 - "GET /health/readiness HTTP/1.1" 200 OK
09:40:06 - LiteLLM Proxy:ERROR: user_api_key_auth.py:1490 - No LiteLLM Virtual Key pass. Please set header=x-litellm-key: Bearer <api_key>
The application itself is functioning correctly, but this error message keeps repeating, cluttering the logs.
Expected Behavior
• The /health/liveliness and /health/readiness endpoints should be accessible without requiring authentication.
• The logs should not be flooded with authentication errors when probes are executed.
Actual Behavior
• The logs keep showing the error:
"No LiteLLM Virtual Key pass. Please set header=x-litellm-key: Bearer <api_key>"
• This happens even though health probes return 200 OK and everything works fine.
already test this in my kubernetes with and without httpHeader, tried also calling the endpoint with a curl e it gives me 200:
readinessProbe:
httpGet:
path: /health/readiness
scheme: HTTP
port: 8080
httpHeaders:
- name: x-litellm-key
value: "Bearer readiness"
livenessProbe:
httpGet:
path: /health/liveliness
scheme: HTTP
port: 8080
httpHeaders:
- name: x-litellm-key
value: "Bearer liveliness"
Would appreciate any guidance on whether this is intended behavior or a misconfiguration on my side. Let me know if further details are needed!
Relevant log output
INFO: 10.116.161.254:36682 - "GET /health/liveliness HTTP/1.1" 200 OK
INFO: 10.116.161.254:36690 - "GET /health/readiness HTTP/1.1" 200 OK
09:40:06 - LiteLLM Proxy:ERROR: user_api_key_auth.py:1490 - No LiteLLM Virtual Key pass. Please set header=x-litellm-key: Bearer <api_key>
Are you a ML Ops Team?
Yes
What LiteLLM version are you on ?
v1.60.0
Twitter / LinkedIn details
No response
What happened?
I am deploying LiteLLM Proxy on Kubernetes and using ArgoCD for synchronization. The application is running, and both readiness and liveness probes return 200 OK, but the logs are continuously filled with the following error:
INFO: 10.116.161.254:36682 - "GET /health/liveliness HTTP/1.1" 200 OK
INFO: 10.116.161.254:36690 - "GET /health/readiness HTTP/1.1" 200 OK
09:40:06 - LiteLLM Proxy:ERROR: user_api_key_auth.py:1490 - No LiteLLM Virtual Key pass. Please set header=x-litellm-key: Bearer <api_key>
The application itself is functioning correctly, but this error message keeps repeating, cluttering the logs.
Expected Behavior
• The /health/liveliness and /health/readiness endpoints should be accessible without requiring authentication.
• The logs should not be flooded with authentication errors when probes are executed.
Actual Behavior
• The logs keep showing the error:
"No LiteLLM Virtual Key pass. Please set header=x-litellm-key: Bearer <api_key>"
• This happens even though health probes return 200 OK and everything works fine.
already test this in my kubernetes with and without httpHeader, tried also calling the endpoint with a curl e it gives me 200:
Would appreciate any guidance on whether this is intended behavior or a misconfiguration on my side. Let me know if further details are needed!
Relevant log output
Are you a ML Ops Team?
Yes
What LiteLLM version are you on ?
v1.60.0
Twitter / LinkedIn details
No response