Python: [Bug]: Duplicate LLM Telemetry Emission #4675

Activity

1. Shawn Henry (sphenry)

   added the

   Bug

   issue type on Mar 13, 2026
2. Shawn Henry (sphenry)

   added

   bugUsage: [Issues], Target: all issues (Legacy, prefer issue type: bug)Usage: [Issues], Target: all issues (Legacy, prefer issue type: bug)

   on Mar 13, 2026
3. Mark Wallace (markwallace-microsoft)

   added

   pythonUsage: [Issues, PRs], Target: PythonUsage: [Issues, PRs], Target: Python

   on Mar 13, 2026
4. Shawn Henry (sphenry)

   assigned

   Eduard van Valkenburg (eavanvalkenburg)

   on Mar 13, 2026
5. Eduard van Valkenburg (eavanvalkenburg)

   added this to Agent Frameworkon Mar 13, 2026
6. Eduard van Valkenburg (eavanvalkenburg)

   moved this to In Review in Agent Frameworkon Mar 13, 2026
7. eavanvalkenburg commented on Mar 13, 2026

   

   Eduard van Valkenburg (eavanvalkenburg)

   on Mar 13, 2026

   Member

   More actions

   I have a fix up in PR #4685:

   • Python: avoid duplicate agent response telemetry #4685

   The change uses ContextVar-based ownership so the outer agent span stops duplicating gen_ai.response.id and token-usage telemetry that already belongs to the inner chat span, while still preserving agent-level response telemetry for agents that do not rely on a chat client.
8. Eduard van Valkenburg (eavanvalkenburg)

   closed this as completedin #4685on Mar 20, 2026
9. github-project-automation

   moved this from In Review to Done in Agent Frameworkon Mar 20, 2026