skills.rest
majiayu000
majiayu000COMMUNITY
Explore all skills by this author →
GitHub

observability-architecture

Configure Prometheus metrics, OpenTelemetry traces, and JSON logs for LiteLLM gateway.

104|19|Updated Jul 15, 2025
Search Tags:#logging#observability#tracing#prometheus#alerting#opentelemetry#health-checks
One-click install
npx skills add https://github.com/majiayu000/litellm-rs --skill observability-architecture
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: observability-architecture
Source: https://github.com/majiayu000/litellm-rs/tree/main/.claude/skills/observability-architecture
Command: npx skills add https://github.com/majiayu000/litellm-rs --skill observability-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

LiteLLM gateway lacks unified visibility across its operations, making it hard to monitor performance, reliability, and security. This skill provides Prometheus metrics, OpenTelemetry tracing, and structured logging to give operators a full observability view.

Core Features & Use Cases

  • Metrics collection with Prometheus-compatible endpoints for dashboards and alerting.
  • Distributed tracing via OpenTelemetry to diagnose latency and failure paths.
  • Structured logging (JSON) for correlation across services, health checks, and incident response.
  • Health checks and alerting integration to detect degradations and trigger responses.

Quick Start

Configure and enable the observability stack in LiteLLM gateway, then access the /metrics endpoint, trace requests with OTLP, and view logs in your logging backend.

Frequently Asked Questions about observability-architecture

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up observability for a LiteLLM gateway?▼

To set up LiteLLM gateway observability, configure the observability stack to enable Prometheus-compatible metrics endpoints, OpenTelemetry tracing, and structured JSON logs for monitoring and troubleshooting.

What is needed to monitor LiteLLM gateway performance and reliability?▼

Monitoring LiteLLM gateway performance requires integrating Prometheus metrics, OpenTelemetry distributed tracing, and structured logging to gain end-to-end visibility across operations and detect degradations.

Can I use Prometheus and OpenTelemetry to trace LiteLLM gateway requests?▼

Yes, you can use Prometheus and OpenTelemetry to trace LiteLLM gateway requests by exporting OTLP traces to diagnose latency and failure paths while scraping the Prometheus-compatible /metrics endpoint.

How do I configure health checks and alerting for LiteLLM?▼

You configure health checks and alerting for LiteLLM by enabling the observability stack, which provides health endpoints and alert rules to detect degradations and trigger incident response actions.

Does LiteLLM observability support structured JSON logs for incident response?▼

Yes, LiteLLM observability supports structured JSON logs for incident response, enabling operators to correlate logs across services during troubleshooting and health check monitoring.

Related Skills

Explore More Software Engineering Skills→
cedriczielcedricziel

opentelemetry-go

Instrument Go applications with OpenTelemetry for traces, metrics, and OTLP export.

Community
Advanced
Prathmesh2000Prathmesh2000
1

observability-engineer

Instrument JSON logs, OpenTelemetry traces, and metrics for cloud-native observability.

Community
Advanced
timequitytimequity
6

monitoring-setup

Set up Prometheus, Grafana, Loki, and Jaeger for Kubernetes observability.

Official
Advanced
ZpankzZpankz
7

Observability Instrumentation

Instrument Go services with structured logs, Prometheus metrics, and OpenTelemetry traces.

Community
Advanced