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

Prototype agent lifecycle events (semconv #445) across LangGraph, CrewAI and ADK

Open
#537 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39
Forks
63
Avg merge
1d 15h
Merged PRs (30d)
175

Description

On open-telemetry/semantic-conventions-genai#445, lmolkova asked for real instrumentation over two or three libraries in this repo as evidence for the candidate gen_ai.agent.paused / gen_ai.agent.checkpointed / gen_ai.agent.resumed events, instead of hand-emitted reference scenarios.

Plan, one PR each:

  • LangGraph: extend the langchain instrumentation. Draft up as #536.
  • CrewAI: fill in the existing skeleton package via CrewAI's event bus (flow persistence, human feedback, checkpoints).
  • ADK: ADK ships its own OpenTelemetry tracing, so this would be a plugin rather than an instrumentation package. Open to guidance on whether it belongs in this repo at all.

Candidate event names stay pending the semconv proposal, the same approach as #507 and semantic-conventions-genai#483. Flagging before starting the CrewAI and ADK work in case the direction or the split should differ.

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 reading semantic-conventions-genai#445, #507, semantic-conventions-genai#483, and the LangGraph draft #536. Then inspect the existing CrewAI skeleton and determine how its event bus can expose persistence, human feedback, and checkpoint events. Done requires an agreed split and direction, plus real CrewAI instrumentation; ADK scope remains an open plugin decision.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, observability-sre
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
32/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.