# Deployment **URL:** https://forum.langchain.com/c/help/langsmith-deployment/6.md [Latest](https://forum.langchain.com/latest.md) · [Categories](https://forum.langchain.com/categories.md) · [Tags](https://forum.langchain.com/tags.md) --- ## [About the Deployment category](https://forum.langchain.com/t/about-the-deployment-category/10)
**Author:** [@crystalr](https://forum.langchain.com/u/crystalr)\ **Replies:** 0\ **Last updated:** [April 22, 2025, 7:14pm UTC](https://forum.langchain.com/t/about-the-deployment-category/10 "2025-04-22T19:14:31Z")
Questions, issues, and/or discussions regarding LangSmith Deployment or Studio. --- ## [POST /threads/{id}/history and updateState return 500 on factory graphs: '\_ReadRuntime' object has no attribute 'context' in the gRPC checkpointer](https://forum.langchain.com/t/post-threads-id-history-and-updatestate-return-500-on-factory-graphs-readruntime-object-has-no-attribute-context-in-the-grpc-checkpointer/4761)
**Author:** [@arthurtran-drova](https://forum.langchain.com/u/arthurtran-drova)\ **Replies:** 0\ **Last updated:** [October 16, 2026, 4:55am UTC](https://forum.langchain.com/t/post-threads-id-history-and-updatestate-return-500-on-factory-graphs-readruntime-object-has-no-attribute-context-in-the-grpc-checkpointer/4761 "2026-10-16T04:55:53Z")
Impact On our LangSmith Deployment, for any thread on our main graph: POST /threads/{id}/history (client.threads.getHistory) returns HTTP 500. POST /threads/{id}/state (client.threads.updateState) returns HTTP 500. GET… --- ## [Managed Deep Agents: can the model be chosen at runtime, without redeploying?](https://forum.langchain.com/t/managed-deep-agents-can-the-model-be-chosen-at-runtime-without-redeploying/4595)
**Author:** [@dilip](https://forum.langchain.com/u/dilip)\ **Replies:** 2\ **Last updated:** [September 23, 2026, 1:12pm UTC](https://forum.langchain.com/t/managed-deep-agents-can-the-model-be-chosen-at-runtime-without-redeploying/4595 "2026-09-23T13:12:52Z")
I’d like users of our app to pick between provider models (Gemini / GPT / Claude) on a deployed Managed Deep Agent. The model seems fixed at deploy time, and the two overrides I’d expect to work are accepted and then sil… --- ## [The Right Solution/Architecture?](https://forum.langchain.com/t/the-right-solution-architecture/4522)
**Author:** [@ipatchcables](https://forum.langchain.com/u/ipatchcables)\ **Replies:** 3\ **Last updated:** [September 13, 2026, 12:27am UTC](https://forum.langchain.com/t/the-right-solution-architecture/4522 "2026-09-13T00:27:41Z")
I’m trying to build out a project that helps automate web testing work (I’m a dev - 100s over servers internally). I’m curious what approach would work best? I know it can’t be fully non-deterministic, but curious what t… --- ## [Best practice for Git-managed Deep Agents skills and thread versioning](https://forum.langchain.com/t/best-practice-for-git-managed-deep-agents-skills-and-thread-versioning/4288)
**Author:** [@beubeu13220](https://forum.langchain.com/u/beubeu13220)\ **Replies:** 3\ **Last updated:** [August 6, 2026, 5:01pm UTC](https://forum.langchain.com/t/best-practice-for-git-managed-deep-agents-skills-and-thread-versioning/4288 "2026-08-06T17:01:55Z")
Hi everyone, We use deepagents==0.6.8 on LangSmith Deployment and are looking for the recommended architecture for skills. Our skills are immutable at runtime. Git is the source of truth: changes are reviewed through G… --- ## [403 Forbidden on POST /runs/multipart despite valid API key](https://forum.langchain.com/t/403-forbidden-on-post-runs-multipart-despite-valid-api-key/4294)
**Author:** [@Bhanu](https://forum.langchain.com/u/Bhanu)\ **Replies:** 1\ **Last updated:** [August 4, 2026, 8:53pm UTC](https://forum.langchain.com/t/403-forbidden-on-post-runs-multipart-despite-valid-api-key/4294 "2026-08-04T20:53:17Z")
The exact error: 403 Client Error: Forbidden for url: https://api.smith.langchain.com/runs/multipart That curl -H “x-api-key: …” https://api.smith.langchain.com/info returns 200 successfully Your LangSmith SDK version … --- ## [Best practice for per-tenant model config and BYOK with LangGraph Cloud\`](https://forum.langchain.com/t/best-practice-for-per-tenant-model-config-and-byok-with-langgraph-cloud/4060)
**Author:** [@beubeu13220](https://forum.langchain.com/u/beubeu13220)\ **Replies:** 5\ **Last updated:** [July 21, 2026, 9:14pm UTC](https://forum.langchain.com/t/best-practice-for-per-tenant-model-config-and-byok-with-langgraph-cloud/4060 "2026-07-21T21:14:22Z")
Hi everyone, I’m looking for best practices for a multi-tenant SaaS agent deployed on LangGraph / LangSmith Cloud. Context: Each customer/org may have its own model configuration. Some orgs may use different provider… --- ## [Long-running run getting cancelled by aggressive workers scale down](https://forum.langchain.com/t/long-running-run-getting-cancelled-by-aggressive-workers-scale-down/4126)
**Author:** [@arthurtran-drova](https://forum.langchain.com/u/arthurtran-drova)\ **Replies:** 5\ **Last updated:** [July 13, 2026, 1:18pm UTC](https://forum.langchain.com/t/long-running-run-getting-cancelled-by-aggressive-workers-scale-down/4126 "2026-07-13T13:18:44Z")
Hi LangChain team, recently we are experiencing some issues related to some of our graph runs getting cancelled (asyncio.CancelledError) in the LangSmith tracing in our Production deployment. After some debugging using … --- ## [Langsmith-fleet issue](https://forum.langchain.com/t/langsmith-fleet-issue/3873)
**Author:** [@coder-jeffery](https://forum.langchain.com/u/coder-jeffery)\ **Replies:** 1\ **Last updated:** [June 4, 2026, 5:01am UTC](https://forum.langchain.com/t/langsmith-fleet-issue/3873 "2026-06-04T05:01:16Z")
when i use gpt 5.5 / kimi2.6 also have this issue: The API key you entered is invalid. Please check your API key settings and try again. --- ## [Could RAG pipelines realistically cause deployment timeouts, is Render suitable for first-time RAG deployments?](https://forum.langchain.com/t/could-rag-pipelines-realistically-cause-deployment-timeouts-is-render-suitable-for-first-time-rag-deployments/3727)
**Author:** [@NjiruWinfred](https://forum.langchain.com/u/NjiruWinfred)\ **Replies:** 3\ **Last updated:** [May 19, 2026, 8:23am UTC](https://forum.langchain.com/t/could-rag-pipelines-realistically-cause-deployment-timeouts-is-render-suitable-for-first-time-rag-deployments/3727 "2026-05-19T08:23:42Z")
I built my first RAG-based AI education chatbot using Python + MongoDB vector storage, but deployment on Render fails with “No open ports detected.” I’m trying to figure out if this is caused by slow RAG startup, embeddi… --- ## [Langgraph deploy CLI cannot deploy to EU Langsmith Cloud](https://forum.langchain.com/t/langgraph-deploy-cli-cannot-deploy-to-eu-langsmith-cloud/3730)
**Author:** [@arthurtran-drova](https://forum.langchain.com/u/arthurtran-drova)\ **Replies:** 6\ **Last updated:** [May 19, 2026, 2:56am UTC](https://forum.langchain.com/t/langgraph-deploy-cli-cannot-deploy-to-eu-langsmith-cloud/3730 "2026-05-19T02:56:12Z")
Hi team, I am trying to deploy our langgraph agents to our EU LangSmith Cloud using langgraph deploy CLI instead of using the UI (which we already used to deploy successfully a few deployments). I set up our Github Acti… --- ## [How are you validating LangChain agent output before it executes shell commands?](https://forum.langchain.com/t/how-are-you-validating-langchain-agent-output-before-it-executes-shell-commands/3656)
**Author:** [@Elmahrosa-Steward](https://forum.langchain.com/u/Elmahrosa-Steward)\ **Replies:** 1\ **Last updated:** [May 4, 2026, 2:40pm UTC](https://forum.langchain.com/t/how-are-you-validating-langchain-agent-output-before-it-executes-shell-commands/3656 "2026-05-04T14:40:32Z")
Been running LangChain agents in production for a few months and kept hitting the same anxiety: the agent generates a shell command or installs a package, and I have no systematic way to validate it before it runs. Tr… --- ## [First Bedrock call after idle is slow on TTFT (follow-ups in the same trace are fast)](https://forum.langchain.com/t/first-bedrock-call-after-idle-is-slow-on-ttft-follow-ups-in-the-same-trace-are-fast/3605)
**Author:** [@formertheorist](https://forum.langchain.com/u/formertheorist)\ **Replies:** 1\ **Last updated:** [April 28, 2026, 10:10am UTC](https://forum.langchain.com/t/first-bedrock-call-after-idle-is-slow-on-ttft-follow-ups-in-the-same-trace-are-fast/3605 "2026-04-28T10:10:51Z")
Context We’re running a LangGraph-based agent that calls Amazon Bedrock using the Converse API via langchain-aws ChatBedrockConverse. In LangSmith, traces show that most of the latency on the first model step is inside t… --- ## [How to receive HITL interrupt events via webhook in LangSmith Deployment?](https://forum.langchain.com/t/how-to-receive-hitl-interrupt-events-via-webhook-in-langsmith-deployment/2033)
**Author:** [@dudiradosezki](https://forum.langchain.com/u/dudiradosezki)\ **Replies:** 3\ **Last updated:** [April 20, 2026, 1:24pm UTC](https://forum.langchain.com/t/how-to-receive-hitl-interrupt-events-via-webhook-in-langsmith-deployment/2033 "2026-04-20T13:24:07Z")
Hi everyone, I have a LangGraph assistant running on LangSmith Deployment (Langgraph Platform). I’m triggering runs successfully from a lambda, providing webhook url and receiving regular status: success webhooks at my… --- ## [I had a few months Experience with across Agent deploys remotegraph calls - old/new dist runtime architecture](https://forum.langchain.com/t/i-had-a-few-months-experience-with-across-agent-deploys-remotegraph-calls-old-new-dist-runtime-architecture/3424)
**Author:** [@johnda98](https://forum.langchain.com/u/johnda98)\ **Replies:** 0\ **Last updated:** [April 16, 2026, 4:17pm UTC](https://forum.langchain.com/t/i-had-a-few-months-experience-with-across-agent-deploys-remotegraph-calls-old-new-dist-runtime-architecture/3424 "2026-04-16T16:17:41Z")
I had a few months Experience with across Agent deploys remotegraph calls - old/new dist runtime architecture Can help if anyone has issue. We did resolve the challenges with architectural changes.. but kept our RAG to… --- ## [Custom routes not working self-hosted standalone](https://forum.langchain.com/t/custom-routes-not-working-self-hosted-standalone/2116)
**Author:** [@mariam-eissa](https://forum.langchain.com/u/mariam-eissa)\ **Replies:** 2\ **Last updated:** [April 15, 2026, 5:27pm UTC](https://forum.langchain.com/t/custom-routes-not-working-self-hosted-standalone/2116 "2026-04-15T17:27:34Z")
we are trying to deploy our agents using the self-host standalone , we added the LANGGRAPH\_AUTH\_TYPE=noop in dockercompose environment . we removed the auth from the config file { "node\_version": "20", "g… --- ## [انشاء وكيل ذكاء اصطناعي](https://forum.langchain.com/t/topic/3345)
**Author:** [@hamdyai1962](https://forum.langchain.com/u/hamdyai1962)\ **Replies:** 1\ **Last updated:** [April 8, 2026, 8:24pm UTC](https://forum.langchain.com/t/topic/3345 "2026-04-08T20:24:13Z")
اريد بناء وكيل ذكاء اصطناعي الوكيل الأكاديمي القانوني الأسمى — Supreme Legal-Academic AI Agent البرومبت الاحترافي الثوري الكامل ╔══════════════════════════════════════════════════════════════════════════════════╗ ║ … --- ## [LangSmith Cloud Deployment Intermittent Issue](https://forum.langchain.com/t/langsmith-cloud-deployment-intermittent-issue/3284)
**Author:** [@mipestan](https://forum.langchain.com/u/mipestan)\ **Replies:** 8\ **Last updated:** [April 3, 2026, 6:54am UTC](https://forum.langchain.com/t/langsmith-cloud-deployment-intermittent-issue/3284 "2026-04-03T06:54:34Z")
Hey, We are observing intermittent issues with our LangSmith Hosted Cloud Deployment. LangGraph API Version: 0.7.90 Deployment Mode: LangSmith Cloud Deployment Type: Development Runtime: Node 20 Below included stackt… --- ## [Redis sentinel with self hosted deployment](https://forum.langchain.com/t/redis-sentinel-with-self-hosted-deployment/3006)
**Author:** [@gdrouet](https://forum.langchain.com/u/gdrouet)\ **Replies:** 5\ **Last updated:** [March 26, 2026, 7:50pm UTC](https://forum.langchain.com/t/redis-sentinel-with-self-hosted-deployment/3006 "2026-03-26T19:50:39Z")
Hello, Is it possible to connect the LangGraph Agent Server to a high-availability Redis setup using Redis Sentinel in a self-hosted deployment? From the documentation, it seems that only standalone Redis or Redis Clus… --- ## [Having issue while using interrupt with Agent Chat UI](https://forum.langchain.com/t/having-issue-while-using-interrupt-with-agent-chat-ui/3217)
**Author:** [@narendrasingodia1998](https://forum.langchain.com/u/narendrasingodia1998)\ **Replies:** 7\ **Last updated:** [March 20, 2026, 8:28am UTC](https://forum.langchain.com/t/having-issue-while-using-interrupt-with-agent-chat-ui/3217 "2026-03-20T08:28:00Z")
Getting i am not able to interrupt i want when human type yes or approved it should so else take feedback import random from dotenv import load\_dotenv from datetime import datetime from typing import TypedDict, Annotat… --- ## [Conflict between dependencies included in the Docker image and langgraph 1.0.9](https://forum.langchain.com/t/conflict-between-dependencies-included-in-the-docker-image-and-langgraph-1-0-9/3041)
**Author:** [@Aurora](https://forum.langchain.com/u/Aurora)\ **Replies:** 2\ **Last updated:** [March 2, 2026, 4:42pm UTC](https://forum.langchain.com/t/conflict-between-dependencies-included-in-the-docker-image-and-langgraph-1-0-9/3041 "2026-03-02T16:42:26Z")
I am looking to update my python project to use langgraph 1.0.9, which includes a fix that bumps the minimum version of orjson from 3.10.1 up to 3.11.5 This is great… however as per the dependencies specified for the … --- ## [Steaming interrupt, if unresolved on reload bad state](https://forum.langchain.com/t/steaming-interrupt-if-unresolved-on-reload-bad-state/2943)
**Author:** [@michael6](https://forum.langchain.com/u/michael6)\ **Replies:** 2\ **Last updated:** [February 13, 2026, 4:49pm UTC](https://forum.langchain.com/t/steaming-interrupt-if-unresolved-on-reload-bad-state/2943 "2026-02-13T16:49:09Z")
I’m using langsmith with deploy. We have an interrupt for human in the loop. The frontend gets the interrupt and we have a way to resolve it. This is ideal flow. However, if on an interrupt, the user reloads the session… --- ## [Langsmith Deployment API key](https://forum.langchain.com/t/langsmith-deployment-api-key/2924)
**Author:** [@all-black-493](https://forum.langchain.com/u/all-black-493)\ **Replies:** 5\ **Last updated:** [February 12, 2026, 10:04pm UTC](https://forum.langchain.com/t/langsmith-deployment-api-key/2924 "2026-02-12T22:04:47Z")
As soon as I deploy my langgraph to the cloud, I am unable to copy the deployment API key and if I try to delete that API key, I must also delete the deployment. I want to get the Deployment API key. --- ## [Errors in server logs checking for long running jobs](https://forum.langchain.com/t/errors-in-server-logs-checking-for-long-running-jobs/2910)
**Author:** [@szabrown](https://forum.langchain.com/u/szabrown)\ **Replies:** 2\ **Last updated:** [February 9, 2026, 3:21pm UTC](https://forum.langchain.com/t/errors-in-server-logs-checking-for-long-running-jobs/2910 "2026-02-09T15:21:54Z")
Every 10 minutes, I’m seeing an error like this in my latest deployment: \[ERROR\] Failed to query long-running queries Traceback (most recent call last): File "/storage/langgraph\_runtime\_postgres/long\_query\_monitor.py"… --- ## [Streaming with custom auth and UseStream not working](https://forum.langchain.com/t/streaming-with-custom-auth-and-usestream-not-working/134)
**Author:** [@samgoos](https://forum.langchain.com/u/samgoos)\ **Replies:** 2\ **Last updated:** [February 6, 2026, 3:05pm UTC](https://forum.langchain.com/t/streaming-with-custom-auth-and-usestream-not-working/134 "2026-02-06T15:05:05Z")
when adding custom auth and then starting langgraph development server (with “disable\_studio\_auth”: false ) auth gets ignored when running the graph directly, but when switching to “chat” we still get a 403. This issue … --- ## [\# \[Bug/Question\] Runtime Context Not Working in Deployed LangSmith Agent - Headers and Config Stripped](https://forum.langchain.com/t/bug-question-runtime-context-not-working-in-deployed-langsmith-agent-headers-and-config-stripped/2705)
**Author:** [@itzhak-lobak](https://forum.langchain.com/u/itzhak-lobak)\ **Replies:** 1\ **Last updated:** [January 15, 2026, 1:51pm UTC](https://forum.langchain.com/t/bug-question-runtime-context-not-working-in-deployed-langsmith-agent-headers-and-config-stripped/2705 "2026-01-15T13:51:05Z")
Summary I’m unable to pass runtime configuration (specifically x-nxty-tenant-id) to my deployed LangGraph agent on LangSmith. Both HTTP headers and request body fields are being stripped/ignored, but the same code works … --- ## [Prod Langsmith deployment raising internal redis errors](https://forum.langchain.com/t/prod-langsmith-deployment-raising-internal-redis-errors/2649)
**Author:** [@KurtzOmer](https://forum.langchain.com/u/KurtzOmer)\ **Replies:** 2\ **Last updated:** [January 5, 2026, 8:32am UTC](https://forum.langchain.com/t/prod-langsmith-deployment-raising-internal-redis-errors/2649 "2026-01-05T08:32:26Z")
Hi team & community, We are currently experiencing a critical issue with our production deployment. Our instance has been down for several hours, and we are seeking an urgent resolution. Deployment Details: - Deployme… --- ## [Europe Langgraph platform threads stuck](https://forum.langchain.com/t/europe-langgraph-platform-threads-stuck/321)
**Author:** [@TomPaolo1](https://forum.langchain.com/u/TomPaolo1)\ **Replies:** 4\ **Last updated:** [December 31, 2025, 1:49pm UTC](https://forum.langchain.com/t/europe-langgraph-platform-threads-stuck/321 "2025-12-31T13:49:03Z")
For the past few days, I’ve noticed that the deployment on the LangGraph platform in Europe can’t even run threads and doesn’t report any issues except that it’s in a busy state and continues running. --- ## [Deployment Error: OpenAIEmbedding Attribute Error](https://forum.langchain.com/t/deployment-error-openaiembedding-attribute-error/2588)
**Author:** [@Ren](https://forum.langchain.com/u/Ren)\ **Replies:** 4\ **Last updated:** [December 25, 2025, 9:33am UTC](https://forum.langchain.com/t/deployment-error-openaiembedding-attribute-error/2588 "2025-12-25T09:33:36Z")
I am writing to you regarding a deployment issue we are facing on the LangSmith Platform. When attempting a deployment on the LangSmith platform, we have been encountering an Attribute Error related to OpenAIEmbedding, … --- ## [Question about the license](https://forum.langchain.com/t/question-about-the-license/2242)
**Author:** [@PlaeryinBol](https://forum.langchain.com/u/PlaeryinBol)\ **Replies:** 6\ **Last updated:** [December 21, 2025, 5:17am UTC](https://forum.langchain.com/t/question-about-the-license/2242 "2025-12-21T05:17:45Z")
Our application is currently failing to deploy in Kubernetes due license verification fail. I want to make sure I understand the licensing correctly: based on my investigation of the langgraph-api source code, I found th… [Next page](https://forum.langchain.com/c/help/langsmith-deployment/6.md?page=1)