Wael Mashal
Wael Mashal
@mattklein123 can help plz ?
@ravenblackx u think its a bug ? or no support for such a scenario ?
@Aisuko yes I am sure I have the service 
Any updates ?
@jatalocks
@wbpcode lets say we set the limit 50 req/minute, and we have 2 requests with **2 different UUIDs** UUID-1 and UUID-2 ### The expected behavior the following ( What I...
@wbpcode can help plz ?
I fixed the issue by changing the the following parts from my original configurations **ratelimit-envoy-filter** metadata_namespace: spfi ---> **metadata_namespace: envoy.lb** key: uri ---> **key: uuid** **uca-spfi-ratelimit-actions** ```yaml patch: operation: MERGE...
@g-linville I have few build in tools tools and one custom tool using llamaindex to read docs (RAG) sys.read, sys.write, sys.exec?, custom-tool Name: custom-tool Description: Get info from test docs...
@g-linville I hope this debug help ```bash root@k8s-poly-gpt-5cbcfc89d9-cvmzg:/app# gptscript --debug-messages kube.gpt 15:56:56 started [main] 15:56:57 sent [main] 15:56:57 messages [request={"model":"gpt-4o","messages":[{"role":"system","content":"\nYou are task oriented system.\nYou receive input from a user, process...