lightrun-ai

Diagnose performance incidents in running services with Lightrun MCP: slow endpoints, latency or SLO regressions, timeouts, deadline-exceeded errors, hangs, and slowness that is intermittent, sporadic, occasional, happens only sometimes, or appears only under load. Use when diagnosing a performance incident; prefer this over lightrun-live-runtime-debugging, including for mixed slow-and-incorrect cases. Use slow-execution snapshots when a duration boundary separates problematic executions; use focused active-path snapshots or call stacks for known hangs that may not reach an end marker. Select the narrowest code section, derive an evidence-based threshold, and correlate captured state with code and telemetry. Use lightrun-live-runtime-debugging for non-performance diagnosis and lightrun-ask-prod for one-off timing, when available; otherwise report the scope gap. Do not use for pull-request review, code changes, setup, deployment, or post-deployment performance validation.

Use when reviewing a pull request with runtime or production evidence — for example to review a PR with runtime verification, gather production evidence, or simulate a patch on live samples. Reviews a pull request by diffing against the PR merge base, collecting live samples, and simulating the patch on captured production inputs.

Diagnose live bugs and incidents that require runtime evidence from a running service using Lightrun MCP. Use when static analysis or logs cannot explain the failure mechanism, when a hypothesis must be tested against live values, timing, or control flow, or when resuming Lightrun async actions. Do not use for one-off production measurements (use lightrun-ask-prod), pull-request review, code changes, setup, or deployment.

Guide deterministic runtime investigations in environments using Lightrun MCP tools, with preflight gating, recovery/resume rules, evidence-first diagnosis, PR-first fix proposal delivery, and local source-code fallback only when PR creation is not possible.

Answer questions about live production system behavior — current variable values, execution durations, hit counts, and value distributions — by instrumenting running services with Lightrun MCP tools. Use when the question requires live runtime data rather than static code analysis (e.g. "show recent requests to this endpoint", "show the runtime distribution for this operation", "what values appear for this expression in production?", "which branch runs for customer X?"). Do not use for incident diagnosis, pull-request review, code changes, setup, or deployment. Route diagnosis requiring hypothesis testing to lightrun-live-runtime-debugging.