Agent skill · marketing growth · jeremylongshore
langchain-incident-runbook
Triage LangChain 1.0 / LangGraph 1.0 production incidents \u2014 LLM-specific\
Why this skill is useful
Adds a comprehensive incident response runbook with specific SLOs, decision trees, and actionable scripts for managing LangChain incidents that are not commonly documented.
What it needs
Requires langchain-observability, prometheus installed locally. Requires pagerduty account access. About 8k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
LangChain Incident Runbook Overview 3:07am. PagerDuty: "LangChain p95 latency > 10s for 5 minutes." You open LangSmith, filter by service="triage-agent" over the last 15 minutes, and the first trace is 43 seconds long — an agent is on step 24 of 25 iterations, bouncing between the same two tools on a vague user prompt ("help me with my account"). The cost dashboard shows $400 spent in the last 10 minutes, up from a $6/hour baseline. This is P10: createreactagent defaults to recursionlimit=25 with no cost cap; vague prompts never converge; the spend hits before GraphRecursionError surfaces. First move is not to push a code fix — it is to flip recursionlimit=5 via config reload and add a middleware token-budget cap per session, then deal with the stuck sessions. Or: same alert, different signature. p95 is healthy at 1.8s, but p99 is 12s and spiky. The spikes correlate with instance starts in Cloud Run. P36: Python + LangChain + embedding preloads = 5–15s cold start; Cloud Run scales to zero by default, so first-request p99 is 10x p95. First move is --min-instances=1 (or a keepalive pinger), not more CPU. The shape of the page decides the first move. This runbook gives you: 1. The LLM-specific SLO set most teams do not have: p95 TTFT <1s, p99 total latency <10s, error-rate <0.5%, cost-per-req <$0.05 — with Prometheus burn-rate recording rules that page on user-visible regression. 2. A triage decision tree with three root paths (latency / cost / error-rate), each with a 3-step diagnostic and first-response action. 3. Provider outage runbook wired to .withfallbacks(backup) so failover is a config flip, not a code change. 4. Agent-loop containment via recursionlimit tuning and middleware token-budget caps so runaway agents stop burning cost before the GraphRecursionError. 5. Post-incident debug bundle (cross-ref langchain-debug-bundle) and write-up template. Pinned: langchain-core 1.0.x, langgraph 1.0.x, langsmith 0.3+. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/langchain-incident-runbook--eca116