Skip to content

feat(telemetry): add lightweight serving telemetry#425

Draft
ClSlaid wants to merge 2 commits into
openinfer-project:mainfrom
ClSlaid:feat/telemetry-system-review
Draft

feat(telemetry): add lightweight serving telemetry#425
ClSlaid wants to merge 2 commits into
openinfer-project:mainfrom
ClSlaid:feat/telemetry-system-review

Conversation

@ClSlaid

@ClSlaid ClSlaid commented Jun 19, 2026

Copy link
Copy Markdown

Summary

  • add lightweight frontend telemetry with OpenInfer /metrics, optional request logs/traces, /openinfer/traces, and caller-owned OTLP payload export
  • centralize sparse request lifecycle tracing and metrics facade counters at the shared engine TokenSink boundary
  • keep success traces at DEBUG, rejected requests at WARN, execution failures at ERROR, and omit per-token tracing/metrics from the shared serving path
  • keep reduce_request focused on output folding and add frontend/sim coverage for the telemetry routes

Tests

  • cargo test --release -p openinfer-engine --lib
  • cargo test --release -p openinfer-vllm-frontend --lib
  • cargo test --release -p openinfer-sim --test frontend_e2e simulated_engine_serves_openai_completions_over_http -- --nocapture
  • cargo fmt --check
  • git diff --check

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant