I tested this branch with a small external claw-vault plugin against a real OpenRouter model key stored in Vault. The plugin repo is here:
git@github.com:sallyom/claw-vault.git
The key point for this PR is that OpenClaw uses a normal SecretRef:
| #!/bin/bash | |
| # Simple script to list available Claude models in Vertex AI using gcloud CLI | |
| # | |
| # Usage: | |
| # ./list-vertex-models.sh [REGION] | |
| # | |
| # Example: | |
| # ./list-vertex-models.sh us-east5 | |
| set -e |
| #!/bin/bash | |
| # Load generation script with malformed requests to trigger error metrics | |
| # Usage: ./generate-load-llmd.sh [duration_minutes] | |
| set -e | |
| ENDPOINT="http://localhost:8080/v1" | |
| DURATION_MINUTES=${1:-5} | |
| MODEL_NAME="Qwen/Qwen3-0.6B" |
This document provides PromQL queries for monitoring LLM-D deployments using Prometheus metrics. The provided load generation script will populate error metrics for testing.
| Metric Need | PromQL Query |
|---|---|
| Overall Error Rate (Platform-wide) | sum(rate(inference_model_request_error_total[5m])) / sum(rate(inference_model_request_total[5m])) |
This document provides an overview of all metrics generated by the llm-d components.
The llm-d system uses Prometheus as the primary metrics collection framework, with metrics covering inference performance, resource utilization,
error rates, and energy consumption across multiple components.
| See the tutorial below. |
| #!/usr/bin/env bash | |
| set -o errexit | |
| # Create a container | |
| container=$(buildah from alpine) | |
| # Run this from wherever the built binaries are available | |
| buildah config --label maintainer="Sally O'Malley <somalley@redhat.com>" $container |
| apiVersion: v1 | |
| kind: Namespace | |
| metadata: | |
| name: rekor-system | |
| labels: | |
| openshift.io/cluster-monitoring: true | |
| --- | |
| apiVersion: rbac.authorization.k8s.io/v1 | |
| kind: Role | |
| metadata: |
| $ df -Th | |
| Filesystem Type Size Used Avail Use% Mounted on | |
| devtmpfs devtmpfs 3.8G 0 3.8G 0% /dev | |
| tmpfs tmpfs 3.8G 0 3.8G 0% /dev/shm | |
| tmpfs tmpfs 3.8G 25M 3.8G 1% /run | |
| /dev/mapper/rhel-root xfs 70G 5.4G 64G 8% / | |
| /dev/vda1 xfs 794M 214M 581M 27% /boot | |
| /dev/vda2 vfat 200M 8.0K 200M 1% /boot/efi | |
| tmpfs tmpfs 777M 0 777M 0% /run/user/1000 | |
| ---------------------------------------------------------- |
| #!/bin/bash | |
| ### Run `make sigstore-testenv-up` from local checkout of containers/skopeo before running this script. | |
| ### This script must run from local checkout of sigstore/sigstore | |
| set -ex | |
| echo "running tests" | |
| export VAULT_TOKEN=testtoken |