Agent frameworks

LangChain and LangGraph tracing

Chains, graphs and their tool calls land as nested spans; LangChain tools are automatic, no trace_tool needed.

Set up LangChain and LangGraph

The snippet is copied from the SDK README, not paraphrased. Keys shown as tk_live_... are the environment key from Settings › Environments.

Python

import evalkit

evalkit.init(
    subscription_key="tk_live_...",   # Dashboard → Settings → Tracing
    service_name="my-service",
)

Copied from sdk-py/README.md § Quick start

Install → first trace

01
Install the SDK
pip install syntropylabs-evalkit or npm install syntropylabs-evalkit.
02
Call init() once
Pass your environment key and a service name, as early as possible in the process, before other modules run requests.
03
Run one chain or graph
No wrapper and no decorator: the call is traced automatically with model, latency and tokens.
04
Open the first trace
Traces shows the call as a span; the environment’s quickstart page ticks when it arrives.

Sample data in the product’s own table. Hover, focus or tap a claim to see the columns it points at.

Sample run

Operation	Service	Status	Model	Latency	Tokens	≈Cost	Score
support_agent.turn8f3a1c0d94e2session sess_4b1e	support-api	ok	gpt-4o-mini	1.84 s	3,412	$0.0006	92%auto
refund_agent.turnc21d7e5a30b8session sess_9a02tool loop	refund-worker	ok	claude-sonnet-4	4.31 s	7,905	$0.0389	68%auto
claude-code.turn5be04f7d1a96session sess_f77c	Claude Code	unset	claude-sonnet-4	48.20 s	61,208	$0.19	—
rag.answere9a2b6c4d015error	docs-bot	error	gpt-4o	6.02 s	9,880	$0.0312	41%auto
voice.turn17c8d3f2a4e0session sess_20d1	ivr-agent	ok	gpt-4o-realtime	0.92 s	1,104	$0.0071	—

fig. 1 · the traces table this integration fills · sample data

Taken from the SDK READMEs’ coverage tables. with flag means the signal leaves your machine only when you opt in.

What Syntropylabs shows for LangChain and LangGraph
Signal	Captured	Detail
Chain and graph runs as nested spans	yes	—
LangChain tool calls with output	yes	LangChain tools are automatic
Model calls made inside the chain	yes	through the auto-instrumented provider clients
Time to first token on streams	no	not in either README’s streaming-latency list
Prompts and completions	yes	on by default; capture_content=False / captureContent: false keeps every metric and drops every payload
Your own functions	partial	on by default in Python for your app’s source tree; opt-in in TypeScript with traceFunction, traceTool or @Traced

LangGraph is named in the Python README (LangChain / LangGraph); the TypeScript README names LangChain.
Time to first token is documented per provider client, not for LangChain itself.
Cost is computed from the model catalogue’s price sheet in the browser, not reported by the provider, and is shown as approximate.

Trace LangChain and LangGraph today

Tracing is free for one project on every plan, coding-agent traces included. Evaluations, datasets and simulation are Pro and up.