Skip to content

Instantly share code, notes, and snippets.

View nerdalert's full-sized avatar
🐈
🦀 🐿

Brent Salisbury nerdalert

🐈
🦀 🐿
View GitHub Profile

PR Output: add --dump / -T CLI flag for effective config output

# dump a real config with conditions
  cargo run --quiet --bin praxis -- -T -c examples/configs/pipeline/conditional-filters.yaml 2>/dev/null

# Output

config_source: examples/configs/pipeline/conditional-filters.yaml

PR Validation Output: Add --validate / -t CLI flag for config checking

  • Add --validate / -t flag that loads and fully validates configuration then exits without starting the proxy
  • Validation runs the same pipeline resolution as server startup (filter instantiation, chain expansion, ordering checks, body limits)
  • Normal server startup unchanged when flag is absent
# Validate the built-in default config (should exit 0, no output)
cargo run -p praxis -- -t

Validation of experimental e2e of agentic Praxis support

Full code for the demo here

./target/debug/praxis --config /tmp/mcp-gateway-two-backends.yaml &
cd <directory with the script at the bottom>
source .venv/bin/activate
MCP_SERVER_NAME=weather uvicorn dev_mcp:app --host 127.0.0.1 --port 8001 &
MCP_SERVER_NAME=calendar uvicorn dev_mcp:app --host 127.0.0.1 --port 8002 &

MCP Queries

  GPU deep dives:
  - "What is the GPU temperature and power draw right now?"
  - "Show me tensor core activity and memory bandwidth utilization on the GPU"
  - "What are the SM and memory clock speeds — is the GPU throttling?"
  - "How much VRAM is used vs free on each GPU?"
  - "Show me PCIe throughput on the GPU node"

Manual Validation for Prometheus metrics foundation with /metrics admin endpoint PR

Validation output are inline after the curl cmds

Start Praxis and a dummy endpoint:

cargo run -p praxis -- -c examples/configs/operations/admin-interface.yaml
python3 -m http.server 3000 both running.

Manual Validation of Praxis JSON-RPC 2.0 foundation for method-based routing

Validation

  ### 1. Build Praxis with JSON-RPC Filter
  ```bash
  cargo build --release -p praxis

 2. Use Simple netcat Backend

Failed attempts at HTTPRoute Host Header Filter Removal

Background

The ExternalModel reconciler creates an HTTPRoute with a RequestHeaderModifier filter that sets Host: <provider-endpoint> (e.g., Host: api.openai.com). This filter was questioned during PR #709 review — could BBR handle this instead, since BBR already handles path rewriting and API key injection?

We investigated whether the filter could be moved into BBR's ext-proc pipeline so that all request mutations happen in a single place.

Attempts

ExternalModel Deployment & Validation Guide

Prerequisites

  • OpenShift cluster with oc/kubectl access as cluster-admin
  • MaaS repo cloned (e.g., ~/istio-gw/prs/4-rconciler-namespace-path/models-as-a-service)

Step 1: Deploy MaaS with ODH Operator

External Model Validation

#!/bin/bash
GW_HOST=$(kubectl get gateway maas-default-gateway -n openshift-ingress -o jsonpath='{.spec.listeners[0].hostname}')
TOKEN=$(oc whoami -t)

echo "Gateway: $GW_HOST"
echo ""

Validation of PR ns prefix to ExternalModel HTTPRoute path for llmisvc parity

PR #709 - re-validation and updated as of 4/11 12:06AM EST

$ HOST="https://maas.$(kubectl get ingress.config.openshift.io/cluster -o jsonpath='{.spec.domain}')"
  TOKEN=$(oc whoami -t)

$ API_KEY=$(curl -sSk -X POST "$HOST/maas-api/v1/api-keys" \
    -H "Authorization: Bearer $TOKEN" \