I tried setting the environment via metadata using the env and environment keys, but the Env filter in Langfuse still only shows the default option, even though the key does appear in the metadata object. So it seems like the environment isn’t being properly recognized. Maybe Langfuse doesn’t expect the environment to be set via metadata, but rather as an environment variable (LANGFUSE_TRACING_ENVIRONMENT) or a specific parameter, as mentioned here: https://langfuse.com/docs/tracing-features/environments https://cdn.discordapp.com/attachments/1396969392083828927/1396969392256061612/Screenshot_2025-07-21_at_4.30.30_PM.png?ex=688004a1&is=687eb321&hm=409a7fc2492256dd22c9d8b687b8d31797254822bd8671b7c318a6573c481ba7& https://cdn.discordapp.com/attachments/1396969392083828927/1396969392553594880/Screenshot_2025-07-21_at_4.29.34_PM.png?ex=688004a1&is=687eb321&hm=d3177153dfa8bce8276f38f0f5ab75c3fca7fc243cf107f5cb414f0b18c23f45&

Langfuse doesn’t recognize the env key in metadata instead, set the environment using the LANGFUSE_TRACING_ENVIRONMENT variable or pass it directly as an environment parameter when initializing the Langfuse client..

ok, but how to do that in VAPI?

Set the Langfuse environment using observabilityPlan.environment, not in metadata, to ensure it’s recognized correctly.. https://docs.vapi.ai/providers/observability/langfuse

that didn't work for me. The Env filter still keep Default as only option. Did I miss something? https://cdn.discordapp.com/attachments/1396969392083828927/1396983829570261054/Screenshot_2025-07-21_at_5.31.00_PM.png?ex=68801213&is=687ec093&hm=5d4168fe21e299d80dd1150c1a46669ffac3b6923dcb30e33a73d7954b99e14f&

use LANGFUSE_TRACING_ENVIRONMENT or set the environment in the Langfuse client directly instead..

I wish VAPI would allow me to do that

Hi, First off, we want to sincerely apologize for the delay in getting back to you. We understand how frustrating it is to wait - especially when you're counting on us - and we owe you a clear explanation of what’s been happening and how we’re addressing it. Over the past few weeks, we've seen a significant increase in support requests. While this reflects exciting growth, it has also stretched our small team and exposed some real challenges in scaling our support operations. To improve your experience, we’ve taken a step back to reassess our approach. Here’s what we’re implementing: - Smarter Support Through Automation: We’re investing in our AI support systems to help you resolve issues more efficiently. Soon, our support bot will offer expanded capabilities, making it easier to access accurate, instant help—particularly for common or repetitive queries. - Expanding the Support Team: To meet growing demand, we’re adding 2–3 new team members focused on managing support volume and improving response times. - Prioritized SLAs for High-Usage Accounts: We’re introducing service level improvements for users who are growing with us: - Accounts with usage over 1,000 minutes/month will receive prioritized support. - For all general inquiries, we’re establishing a standardized 48-hour response time. We’re confident these steps will lead to faster, more reliable support and help us better serve you as you grow with us. Also, in case you still need help with this ongoing ticket, do let us know, and we will help you get this resolved as soon as possible. Thank you for your continued patience and for being part of our journey. Warm regards, Vapi Team

Hi Vapi Team, Thanks for the update and for being transparent about your support operations. I understand the challenges of scaling and appreciate the steps you're taking to improve. That said, I wanted to confirm that my original issue in this ticket remains unresolved. I’d appreciate a more specific update when possible. Looking forward to hearing from you soon.

@rmaceissoft Hey! I looked into our codebase, and it seems we have two options as of now: 1. Using tags as environment variables, which I believe you are already using this, and we are correctly passing it to the LangFuse, but they are not respecting tags. 2. Setting up separate LangFuse projects per environment, like setting up different LangFuse credentials for each environment. The pros of the first one are: - It works immediately searchable in LangFuse The cons are: - It isn't appearing in environment filter - Less organized into environments For the second option, the pros are: - Complete separation works - But requires multiple credentials management The tag is the ideal choice which has been exposed to us through by LangFuse side. So I'll suggest you check out with them even after applying tags if they are not appearing for continue using tags as a filter to filter traces based on different tags.

@Shubham Bajaj I'm already using approach 1. I assume you meant metadata, right? That said, I strongly recommend that the VAPI team implement a proper solution that aligns with how Langfuse handles environment-based tracing. Here’s a reference: https://gist.github.com/rmaceissoft/6a3813c19ede6b254d9eb59d93b61f28

Hey, thanks for sharing your details. Our team will look into it and get back to you soon with an update.