🐛 Bug Report: openai-agents records every model call as two LLM spans (calls and tokens doubled)
Maintainers usually reply within 1 day
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 35/100
- Issue type
- Bug
- Clarity
- Clearly specified
- Activity status
- Stale
- Tech stack
- python
- Domain
- observability, testing
Research direction
Read the open PR linked to this issue and inspect the OpenAI Agents _hooks.py processor and responses_wrappers.py wrappers. Start by reproducing the span and token counts with the offline httpx.MockTransport example, then check the existing suppression handling in the chat, completion, embedding, and image wrappers. Done means one LLM span per non-streamed model call with the provider's token counts, including the listed failure and turn-limit cases.
Written by the indexing model from the issue text.
Description
Which component is this bug for?
OpenAI Agents Instrumentation (with the OpenAI instrumentation, as Traceloop.init() enables both by default)
📜 Description
With the default Traceloop.init(), every non-streamed model call made through the OpenAI Agents SDK is recorded as two LLM spans: one from the openai-agents processor and one from the OpenAI Responses wrapper. Call counts, latency and token usage in a dashboard are doubled.
Cause: the openai-agents processor does not set SUPPRESS_LANGUAGE_MODEL_INSTRUMENTATION_KEY while its generation/response span is open, and the Responses wrappers (responses_get_or_create_wrapper and its async twin) do not check that key. The chat, completion, embedding and image wrappers already check it.
👟 Reproduction steps
Standalone, offline (httpx.MockTransport), no API key:
"""OpenLLMetry + OpenAI Agents SDK: one model call is recorded as two LLM spans.
Needs traceloop-sdk and openai-agents. Offline: httpx.MockTransport answers. Leave OPENAI_API_KEY
unset so the Agents SDK's own exporter skips its upload."""
import asyncio
import httpx
from openai import AsyncOpenAI
from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
from traceloop.sdk import Traceloop
exporter = InMemorySpanExporter()
Traceloop.init(app_name="repro", exporter=exporter, disable_batch=True, telemetry_enabled=False)
from agents import Agent, OpenAIResponsesModel, Runner # noqa: E402
BODY = {"id": "resp_1", "object": "response", "created_at": 0, "status": "completed", "model": "m",
"output": [{"type": "message", "id": "msg_1", "role": "assistant", "status": "completed",
"content": [{"type": "output_text", "text": "Hello!", "annotations": []}]}],
"parallel_tool_calls": True, "tool_choice": "auto", "tools": [],
"usage": {"input_tokens": 11, "output_tokens": 7, "total_tokens": 18,
"input_tokens_details": {"cached_tokens": 0}, "output_tokens_details": {"reasoning_tokens": 0}}}
transport = httpx.MockTransport(lambda request: httpx.Response(200, json=BODY))
client = AsyncOpenAI(api_key="x", base_url="http://fake/v1", http_client=httpx.AsyncClient(transport=transport))
agent = Agent(name="helper", model=OpenAIResponsesModel("m", client))
asyncio.run(Runner.run(agent, "hi"))
llm = [s for s in exporter.get_finished_spans() if s.attributes.get("gen_ai.operation.name") == "chat"]
tokens = sum(s.attributes.get("gen_ai.usage.output_tokens", 0) for s in llm)
print(f"provider requests: 1; LLM spans: {len(llm)}; output tokens on LLM spans: {tokens} (provider sent 7)")
👍 Expected behavior
One LLM span per model call, with the tokens the provider sent (7).
👎 Actual Behavior with Screenshots
provider requests: 1; LLM spans: 2; output tokens on LLM spans: 14 (provider sent 7)
Cases checked (offline fake provider, LLM spans vs real provider requests):
| case | provider requests | LLM spans today |
|---|---|---|
| plain agent run with one tool call | 2 | 4 |
| run whose tool raises | 2 | 4 |
| run whose model call fails | 2 | 4 |
run that hits max_turns |
3 | 6 |
| model calls a tool that does not exist | 1 | 2 |
| streamed runs | n | n (correct) |
🤖 Python Version
3.12
📃 Provide any additional context for the Bug.
traceloop-sdk 0.62.4, opentelemetry-instrumentation-openai-agents 0.62.4, openai-agents 0.23.1, openai 3.28.0. Still the same on main (17d0c5a) and with every open PR that touches _hooks.py or responses_wrappers.py (12 tested). #4060 mentions "double-instrumentation artifacts from two spans per LLM call" in passing; I could not find an issue for it.
I found this with Trueup, an AI agent I am building that runs instrumented apps against a fake provider and compares what really happened with what the trace says. The cases, the repro and the fix in the linked PR were produced by it.
👀 Have you spent some time to check if this bug has been raised before?
- I checked and didn't find similar issue
Are you willing to submit PR?
Yes I am willing to submit a PR!
- Dominant language
- Python
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 2
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing 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.
More from traceloop/openllmetry
-
bug python
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
traceloop/openllmetry#4717 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: Incomplete cache token migration after #4243 breaks Bedrock and Groq instrumentationPossibly taken @Quantum-Enigma-dot claimed this 21 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
traceloop/openllmetry#4665 · 1 comment ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.reasoning_tokens on streamed chat completionsPossibly taken @jayfeng7 claimed this 23 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
traceloop/openllmetry#4660 · 1 comment ·
Maintainers usually reply within 1 day
-
Bug Report: Failed dataset deletes still remove local rows and columnsPossibly taken @inchang-ing claimed this 32 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
traceloop/openllmetry#4630 ·
Maintainers usually reply within 1 day
-
🐛 Bug Report: LiteLLM instrumentation does not record seed, stop, frequency_penalty, presence_penaltyPossibly taken @shantam77 claimed this 38 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
traceloop/openllmetry#4598 · 2 comments ·
Maintainers usually reply within 1 day
All issues in traceloop/openllmetry
Similar issues
-
opensubtitlescom: provider rejects pt-PT even though its own converter maps itPossibly taken @paulo-0308 claimed this today. Open
Difficulty 1/5 Under an hour Newbie friendliness 88/100
Diaoul/subliminal#1405 ·
-
Internal ErrorOpenbug
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
frappe/frappe_docker#2071 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
The-Pocket/PocketFlow#161 ·
-
comp/desktop P2 type/bug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
NousResearch/hermes-agent#157702 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 83/100
zai-org/zcode-plugins#202 ·
Maintainers usually reply within 1 day