open-telemetry / open-telemetry/opentelemetry-python-genai

[agno] Support streaming responses on invoke_agent and invoke_workflow

Open
#556 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

openinference-migration
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.messages on invoke_agent and invoke_workflow

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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.