langchain-otel-observability

name	langchain-otel-observability
description	Wire LangChain 1.0 / LangGraph 1.0 traces into an OpenTelemetry-native backend (Jaeger, Honeycomb, Grafana Tempo, Datadog) with LLM-specific SLOs, safe prompt-content policy, and subgraph-aware span propagation. Use when LangSmith is not the right fit (existing OTEL stack, compliance, multi-cloud) or alongside LangSmith for deep-system traces. Trigger with "langchain OTEL", "langchain opentelemetry", "langchain jaeger", "langchain honeycomb", "langchain SLO", "LLM span", "langchain tempo", "langchain datadog tracing".
allowed-tools	Read, Write, Edit, Bash(python:*), Bash(pip:*)
version	2.5.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","langchain","langgraph","python","langchain-1.0","observability","opentelemetry","jaeger","honeycomb"]
compatibility	Designed for Claude Code, also compatible with Codex

LangChain OTEL Observability (Python)

Overview

An engineer wires OpenTelemetry expecting to see prompts and responses in Honeycomb. The traces land — but only timing, model name, and token counts appear. The prompt body is blank. This is not a bug: it's the OTEL GenAI semantic-conventions privacy-safe default (P27), where OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT is off. The instinct is to flip it on and move on. On a multi-tenant workload that flip is a leak — the next engineer to search traces for Tenant A sees Tenant B's PII in the results, because redaction was supposed to happen upstream and never did.

A second trap lives inside LangGraph. A BaseCallbackHandler attached to the parent runnable never fires on inner agent tool calls, because LangGraph creates a child runtime per subgraph and callbacks do not inherit (P28). Spans inside subgraphs appear orphaned in the waterfall — or they do not appear at all — and SLO dashboards under-count latency on the exact calls that matter most: the nested agent loops.

This skill wires LangChain 1.0 / LangGraph 1.0 into an OTEL-native backend (Jaeger, Honeycomb, Grafana Tempo, Datadog) with a correct content-capture policy, subgraph-aware span propagation, and five LLM-specific SLOs (p95 / p99 latency, error rate, cost-per-request, TTFT) with burn-rate alerts. Pin: langchain-core 1.0.x, langgraph 1.0.x, opentelemetry-instrumentation-langchain >= 0.33, OTEL GenAI semconv as of 2026-04. Pain-catalog anchors: P27, P28 (and cross-references P04, P34, P37).

Prerequisites

• Python 3.10+
• langchain-core >= 1.0, < 2.0, langgraph >= 1.0, < 2.0
• An OTEL-native backend picked: Jaeger (dev), Honeycomb / Tempo / Datadog (prod)
• For multi-tenant: upstream redaction middleware already in place (see langchain-security-basics and langchain-middleware-patterns)
• Access to set env vars at deploy time (OTLP_ENDPOINT, API keys)

Instructions

Step 1 — Install the SDK and instrumentor, configure the exporter

pip install \
  opentelemetry-api \
  opentelemetry-sdk \
  opentelemetry-exporter-otlp-proto-http \
  "opentelemetry-instrumentation-langchain>=0.33"

import os
from opentelemetry import trace
from opentelemetry.sdk.trace  TracerProvider
 opentelemetry.sdk.trace.export  BatchSpanProcessor
 opentelemetry.sdk.resources  Resource
 opentelemetry.exporter.otlp.proto.http.trace_exporter  OTLPSpanExporter
 opentelemetry.instrumentation.langchain  LangchainInstrumentor

resource = Resource.create({
    : ,
    : ,
    : os.getenv(, ),
})
provider = TracerProvider(resource=resource)
provider.add_span_processor(BatchSpanProcessor(
    OTLPSpanExporter(
        endpoint=os.environ[],       
        headers=_parse_headers(os.getenv(, )),
    ),
    max_queue_size=,        
    max_export_batch_size=,  
))
trace.set_tracer_provider(provider)

LangchainInstrumentor().instrument()