🐛 Bug Report: OpenAI Agents: with two concurrent runs of the same agent, a handoff span is recorded in the other run's trace
Mantenedores costumam responder em até 1 dia
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 30/100
- Tipo de issue
- Bug
- Clareza
- Claramente especificada
- Status de atividade
- Estagnada
- Stack de tecnologia
- python
- Domínio
- observability, testing-qa
Direção de pesquisa
Start in the OpenAI Agents SDK instrumentation, especially _start_handoff_span() and _find_agent_span(from_agent), then reproduce the issue with the supplied concurrent run script. Check how each run's trace context is tracked and how the handoff target is named; done when the handoff span appears under run B's assistant.agent span in trace 2. PR #4639 is already open against this issue.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
Which component is this bug for?
OpenAI Instrumentation
📜 Description
Package: opentelemetry-instrumentation-openai-agents (OpenAI Agents SDK instrumentation; it is not in the component list).
When an app runs the same agent twice at the same time (for example a server handling two requests), the handoff span of one run is recorded in the trace of the other run, and the run that handed off has no handoff span in its own trace.
_start_handoff_span() takes the parent from _find_agent_span(from_agent), which searches the open agent spans of all runs by agent name and returns the first match, not the agent span of the handoff's own trace. The handoff span is also named assistant → unknown.handoff, since to_agent is not known yet when the span starts.
👟 Reproduction steps
# OpenAI Agents SDK: two concurrent runs of the same agent (two requests to one app). The handoff span of run B is
# recorded in run A's trace, and run B's trace has no handoff span.
import asyncio, json, sys
from importlib.metadata import version
import openai
try:
import httpx2 as httpx # openai >= 3
except ImportError:
import httpx
from opentelemetry.sdk.trace import SpanProcessor, TracerProvider
from agents import Agent, Runner, function_tool, set_default_openai_client, set_trace_processors
from opentelemetry.instrumentation.openai_agents import OpenAIAgentsInstrumentor
class Spans(SpanProcessor):
def __init__(self): self.ended = []
def on_end(self, span): self.ended.append(span)
spans = Spans(); provider = TracerProvider(); provider.add_span_processor(spans)
SCRIPTS = {"A": ["tool", "text"], "B": ["tool", "handoff", "text"]} # only run B hands off
TURN = {}
def respond(request): # a local stand-in for the Responses API, one script per run
body = json.loads(request.content)
first_user = next(i for i in body["input"] if i.get("role") == "user")
run = first_user["content"].split()[-1] # the user asks "question A" or "question B"
n = TURN[run] = TURN.get(run, 0) + 1
step = SCRIPTS[run][n - 1] if n <= len(SCRIPTS[run]) else "text"
item = {"tool": {"type": "function_call", "id": f"fc_{run}{n}", "call_id": f"call_{run}{n}", "name": "lookup",
"arguments": json.dumps({"q": "weather"}), "status": "completed"},
"handoff": {"type": "function_call", "id": f"fc_{run}{n}", "call_id": f"call_{run}{n}",
"name": "transfer_to_specialist", "arguments": "{}", "status": "completed"},
"text": {"type": "message", "id": f"msg_{run}{n}", "status": "completed", "role": "assistant",
"content": [{"type": "output_text", "annotations": [], "text": f"answer for {run}"}]}}[step]
resp = {"id": f"resp_{run}{n}", "object": "response", "created_at": 0, "status": "completed", "model": "m",
"parallel_tool_calls": True, "tool_choice": "auto", "tools": [], "output": [item],
"usage": {"input_tokens": 3, "output_tokens": 2, "total_tokens": 5,
"input_tokens_details": {"cached_tokens": 0}, "output_tokens_details": {"reasoning_tokens": 0}}}
events = [{"type": "response.created", "response": dict(resp, status="in_progress", output=[])},
{"type": "response.output_item.added", "output_index": 0,
"item": dict(item, status="in_progress", **({"content": []} if item["type"] == "message" else {"arguments": ""}))},
{"type": "response.output_item.done", "output_index": 0, "item": item},
{"type": "response.completed", "response": resp}]
text = "".join(f"event: {e['type']}\ndata: {json.dumps(dict(e, sequence_number=i))}\n\n" for i, e in enumerate(events))
return httpx.Response(200, headers={"content-type": "text/event-stream"}, content=text.encode())
set_trace_processors([]) # no export to OpenAI
set_default_openai_client(openai.AsyncOpenAI(api_key="x", base_url="http://mock/v1", max_retries=0,
http_client=httpx.AsyncClient(transport=httpx.MockTransport(respond))), use_for_tracing=False)
@function_tool
def lookup(q: str) -> str:
"""Look something up."""
return "sunny"
specialist = Agent(name="specialist", instructions="Answer in detail.", model="m")
assistant = Agent(name="assistant", instructions="Answer briefly.", model="m", tools=[lookup], handoffs=[specialist])
async def main():
print(f"opentelemetry-instrumentation-openai-agents {version('opentelemetry-instrumentation-openai-agents')} | "
f"openai-agents {version('openai-agents')} | python {sys.version.split()[0]}")
OpenAIAgentsInstrumentor().instrument(tracer_provider=provider)
run_a = Runner.run_streamed(assistant, "question A") # run A: a tool call, then an answer
run_b = Runner.run_streamed(assistant, "question B") # run B: a tool call, a handoff to the specialist, an answer
async for _ in run_a.stream_events(): # both runs are in flight; the app reads A, then B
pass
async for _ in run_b.stream_events():
pass
traces = {}
for s in sorted(spans.ended, key=lambda s: s.start_time):
traces.setdefault(s.context.trace_id, []).append(s.name)
for i, names in enumerate(traces.values(), 1):
print(f"trace {i}: {names}")
asyncio.run(main())
👍 Expected behavior
Each run's spans are in its own trace: the handoff span is in trace 2, under run B's assistant.agent span.
👎 Actual Behavior with Screenshots
opentelemetry-instrumentation-openai-agents 0.62.4 | openai-agents 0.24.0 | python 3.13.7
trace 1: ['Agent Workflow', 'assistant.agent', 'openai.response', 'lookup.tool', 'openai.response', 'assistant → unknown.handoff']
trace 2: ['Agent Workflow', 'assistant.agent', 'openai.response', 'lookup.tool', 'openai.response', 'specialist.agent', 'openai.response']
🤖 Python Version
3.13 (also seen with 3.12)
📃 Provide any additional context for the Bug.
Trace 1 is run A, which calls the tool and answers; it never hands off. Trace 2 is run B, which calls the tool, hands
off to specialist and answers. opentelemetry-instrumentation-openai-agents 0.62.4 (the latest release; main has no changes to this package since), openai-agents 0.24.0 (also 0.23.1). Related: PR #4097.
👀 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?
None
- Linguagem predominante
- Python
- Estrelas
- 7.5k
- Forks
- 1.2k
- Merge médio
- 1d 23h
- PRs com merge (30d)
- 3
Preparar o ambiente
- Sem Dockerfile nem arquivo Docker Compose
- Tem um modelo de pull request
- Ler o guia de contribuição
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de traceloop/openllmetry
-
🐛 Bug Report: OpenAI Responses: with_raw_response.create() raises when the body can't be parsed, though the uninstrumented call returnsTalvez já em andamento Um pull request vinculado a esta issue está aberto ou já foi mesclado. Abertabug python
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 76/100
traceloop/openllmetry#4717 ·
Mantenedores costumam responder em até 1 dia
-
🐛 Bug Report: Incomplete cache token migration after #4243 breaks Bedrock and Groq instrumentationTalvez já em andamento @Quantum-Enigma-dot assumiu há 21 dias. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 76/100
traceloop/openllmetry#4665 · 1 comentário ·
Mantenedores costumam responder em até 1 dia
-
🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.reasoning_tokens on streamed chat completionsTalvez já em andamento @jayfeng7 assumiu há 23 dias. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 82/100
traceloop/openllmetry#4660 · 1 comentário ·
Mantenedores costumam responder em até 1 dia
-
Bug Report: Failed dataset deletes still remove local rows and columnsTalvez já em andamento @inchang-ing assumiu há 32 dias. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 88/100
traceloop/openllmetry#4630 ·
Mantenedores costumam responder em até 1 dia
-
🐛 Bug Report: LiteLLM instrumentation does not record seed, stop, frequency_penalty, presence_penaltyTalvez já em andamento @shantam77 assumiu há 38 dias. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 85/100
traceloop/openllmetry#4598 · 2 comentários ·
Mantenedores costumam responder em até 1 dia
Todas as issues de traceloop/openllmetry
Issues semelhantes
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 77/100
mozilla-ai/cq#601 ·
Mantenedores costumam responder em até 1 dia
-
Bump Python to 3.14 or 3.15Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 68/100
Mantenedores costumam responder em até 1 dia
-
intcomma returns exponential notation for large floatsTalvez já em andamento @Omarinho12345 assumiu hoje. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 72/100
python-humanize/humanize#521 ·
Mantenedores costumam responder em até 1 dia
-
LUCJ pass manager raises NoEdgeBetweenNodes when an edge is bad for two two-qubit gatesTalvez já em andamento @hat-im assumiu hoje. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 76/100
Mantenedores costumam responder em até 1 dia
-
opensubtitlescom: provider rejects pt-PT even though its own converter maps itTalvez já em andamento @paulo-0308 assumiu hoje. Aberta
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 88/100
Diaoul/subliminal#1405 ·