traceloop / traceloop/openllmetry

🚀 Feature: Select field to send to APM or possibility to obfuscate

Open
#2,171 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
7.4k
Forks
1.1k
Avg merge
8d 14h
Merged PRs (30d)
2

Description

Which component is this feature for?

Anthropic Instrumentation

🔖 Feature description

Sometimes, some fields, like the prompt or results (completion), which are reported thru openllmetry, may contains confidentials values would need not to be reported or maybe obfuscated (replaced by **** ?).

🎤 Why is this feature needed ?

Some customers may want to observe there genAI apps but don't want confidential data at the APM level, which may appears in the prompt or the result.

✌️ How do you aim to achieve this?

give the possibility to omit or obfuscate a field, maybe through env vars?

🔄️ Additional Information

No response

👀 Have you spent some time to check if this feature request has been raised before?
  • I checked and didn't find similar issue
Are you willing to submit PR?

Yes I am willing to submit a PR!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the Anthropic Instrumentation entry point and the code that reports prompts and completions through OpenLLMetry. Review existing configuration patterns before deciding how field omission or obfuscation should be specified, then define tests that verify confidential values are not sent to the APM.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
observability-sre
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.