open-telemetry / open-telemetry/opentelemetry-python-genai
[agno] Support streaming responses on invoke_agent and invoke_workflow
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39
- Forks
- 63
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 175
Description
[!NOTE]
This issue was generated with AI assistance and requires investigation and confirmation prior to being worked on.
Part of #555.
When streaming is enabled (stream=True) on Agent.run/arun, Team.run/arun, or Workflow.run/arun, the methods return an iterator or async iterator. Spans currently close immediately upon returning the iterator before chunks are consumed, missing output content and telemetry finalization. Use stream wrappers to keep spans open until iteration finishes and capture accumulated output messages.
- Semconv mapping:
gen_ai.output.messagesoninvoke_agentandinvoke_workflow
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 with the streaming paths for Agent.run/arun, Team.run/arun, and Workflow.run/arun, then trace how spans are created and closed when stream=True. Use stream wrappers so spans remain open through iterator consumption and verify that output messages and telemetry are finalized after iteration completes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- observability
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100