LangSmith Python SDK memory grows in long-running apps (RunTree kept in memory)

TL;DR

Memory grows steadily over time, but only when LangSmith tracing is enabled. tracemalloc and objgraph show RunTree objects accumulating in memory long after their traces were flushed to the API. langsmith 0.4.27, langchain 0.3.27, langgraph 0.6.7.

Steps

1. Long-running Python app using LangGraph/LangChain (asyncio.gather with create_task, one graph per task). Memory grows steadily over time, but only when LangSmith tracing is enabled. tracemalloc and objgraph show RunTree objects accumulating in memory long after their traces were flushed to the API. langsmith 0.4.27, langchain 0.3.27, langgraph 0.6.7.
2. A maintainer confirmed this is expected behavior rather than a leak: the Python SDK keeps the whole run tree (parents, children, inputs/outputs, metadata) in memory while a trace is live, so RSS grows with concurrency and only releases when the root run finishes. For wide fan-outs or long-running apps, reduce pressure by: upgrading to langsmith 0.4.30+ and setting LANGSMITHEXCLUDECHILDRUNS=true (shipped mitigation, feature-flagged because it can affect custom tracing setups that traverse childruns); limiting concurrency with max_concurrency or an asyncio semaphore; or splitting work into multiple traces under the same LangSmith thread.

Expected: A maintainer confirmed this is expected behavior rather than a leak: the Python SDK keeps the whole run tree (parents, children, inputs/outputs, metadata) in memory while a trace is live, so RSS grows with concurrency and only releases when the root run finishes.

When to use

You are seeing this: Long-running Python app using LangGraph/LangChain (asyncio.gather with create_task, one graph per task). Use this skill when you run into "LangSmith Python SDK memory grows in long-running apps (RunTree kept in memory)".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

Versions mentioned in the source: langsmith 0.4.27, langchain 0.3.27, langgraph 0.6.7, langsmith 0.4.30. If you are on something much newer or older, the details may have shifted.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Question: Long-running Python app using LangGraph/LangChain (asyncio.gather with create_task, one graph per task). Memory grows steadily over time, but only when LangSmith tracing is enabled. tracemalloc and objgraph show RunTree objects accumulating in memory long after their traces were flushed to the API. langsmith 0.4.27, langchain 0.3.27, langgraph 0.6.7.

Verified resolution: A maintainer confirmed this is expected behavior rather than a leak: the Python SDK keeps the whole run tree (parents, children, inputs/outputs, metadata) in memory while a trace is live, so RSS grows with concurrency and only releases when the root run finishes. For wide fan-outs or long-running apps, reduce pressure by: upgrading to langsmith 0.4.30+ and setting LANGSMITHEXCLUDECHILDRUNS=true (shipped mitigation, feature-flagged because it can affect custom tracing setups that traverse childruns); limiting concurrency with max_concurrency or an asyncio semaphore; or splitting work into multiple traces under the same LangSmith thread.

Source: https://github.com/langchain-ai/langsmith-sdk/issues/2009

Thread: https://vectle.com/threads/thr_VrP7M6p3mPVhGVb9KMw7Nw