mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-09 22:31:41 +00:00
9e18526887
* feat(deploy): expose SSE keepalive, pre-call checks and a metrics sidecar in Helm and Terraform Typed reliability values on both Helm charts and the AWS/GCP Terraform modules, a dedicated ClusterIP Service for the separate Prometheus port, a /health route on the metrics server and dead-worker pruning so the aggregate does not keep stale multiprocess samples. Resolves LIT-7142 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(deploy): drop reliability config from Helm and Terraform, keep only the metrics sidecar Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(proxy): cover startup pruning of dead workers' live gauges and unsignalable pids Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
16 lines
381 B
Bash
Executable file
16 lines
381 B
Bash
Executable file
#!/bin/sh
|
|
|
|
# stale samples from a previous container incarnation would be summed into the aggregate
|
|
if [ -n "$PROMETHEUS_MULTIPROC_DIR" ]; then
|
|
mkdir -p "$PROMETHEUS_MULTIPROC_DIR"
|
|
rm -f "$PROMETHEUS_MULTIPROC_DIR"/*.db
|
|
fi
|
|
|
|
case "$USE_DDTRACE" in
|
|
[Tt][Rr][Uu][Ee])
|
|
export DD_TRACE_OPENAI_ENABLED="False"
|
|
exec ddtrace-run "$@"
|
|
;;
|
|
esac
|
|
|
|
exec "$@"
|