🐛 Bug Report: openai-agents records every model call as two LLM spans (calls and tokens doubled)
I maintainer di solito rispondono entro 1 giorno
Valutazione
- Difficoltà
- 3/5
- Tempo stimato
- 1-2 giorni
- Idoneità per principianti
- 35/100
- Tipo di issue
- Bug
- Chiarezza
- Specificata chiaramente
- Stato di attività
- Ferma
- Stack tecnologico
- python
- Ambito
- observability, testing
Direzione di ricerca
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.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
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!
- Lingua principale
- Python
- Stelle
- 7.5k
- Fork
- 1.2k
- Merge medio
- 2g 6h
- PR unite (30g)
- 2
Preparare l'ambiente
- Nessun Dockerfile né file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di traceloop/openllmetry
-
🐛 Bug Report: OpenAI Responses: with_raw_response.create() raises when the body can't be parsed, though the uninstrumented call returnsForse già presa Una pull request collegata a questa issue è aperta o già unita. Apertabug python
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
traceloop/openllmetry#4717 ·
I maintainer di solito rispondono entro 1 giorno
-
🐛 Bug Report: Incomplete cache token migration after #4243 breaks Bedrock and Groq instrumentationForse già presa @Quantum-Enigma-dot l’ha presa 21 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
traceloop/openllmetry#4665 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.reasoning_tokens on streamed chat completionsForse già presa @jayfeng7 l’ha presa 23 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
traceloop/openllmetry#4660 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
Bug Report: Failed dataset deletes still remove local rows and columnsForse già presa @inchang-ing l’ha presa 32 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 88/100
traceloop/openllmetry#4630 ·
I maintainer di solito rispondono entro 1 giorno
-
🐛 Bug Report: LiteLLM instrumentation does not record seed, stop, frequency_penalty, presence_penaltyForse già presa @shantam77 l’ha presa 38 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 85/100
traceloop/openllmetry#4598 · 2 commenti ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di traceloop/openllmetry
Issue simili
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 77/100
mozilla-ai/cq#601 ·
I maintainer di solito rispondono entro 1 giorno
-
Bump Python to 3.14 or 3.15Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
I maintainer di solito rispondono entro 1 giorno
-
intcomma returns exponential notation for large floatsForse già presa @Omarinho12345 l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
python-humanize/humanize#521 ·
I maintainer di solito rispondono entro 1 giorno
-
LUCJ pass manager raises NoEdgeBetweenNodes when an edge is bad for two two-qubit gatesForse già presa @hat-im l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
I maintainer di solito rispondono entro 1 giorno
-
opensubtitlescom: provider rejects pt-PT even though its own converter maps itForse già presa @paulo-0308 l’ha presa oggi. Aperta
Difficoltà 1/5 Meno di un'ora Idoneità per principianti 88/100
Diaoul/subliminal#1405 ·