open-telemetry / open-telemetry/opentelemetry-python-contrib
Update gen AI instrumentations to consistently handle a request failure
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 1.1k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 16
Description
First we need to decide on what the behavior should be: https://github.com/open-telemetry/semantic-conventions-genai/issues/56
Need to see if behavior is consistent between vertex AI / gen ai SDK (and the other instrumentations too). There should still be a log/span when this happens. The error.type attribute should be set on it..
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked semantic-conventions-genai issue to understand the intended request-failure behavior. Compare the Vertex AI, Gen AI SDK, and other instrumentation paths for failures. Done means the behavior is consistent, a log or span is still emitted, and its error.type attribute is set.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, observability
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100