🐛 Bug Report: OpenAI instrumentation drops gen_ai.usage.reasoning_tokens on streamed chat completions
维护者通常 1 天内回复
评估
- 难度
- 2/5
- 预计耗时
- 1-3 小时
- 新手友好度
- 82/100
- Issue 类型
- 缺陷
- 描述清晰度
- 描述清楚
- 活跃度
- 活跃
- 技术栈
- python
调研方向
阅读 shared/chat_wrappers.py,特别是 _handle_response 和 _set_streaming_token_metrics,然后检查 tests/traces/test_chat.py 和 test_chat_reasoning。为包含 completion_tokens_details.reasoning_tokens 的 usage chunk 添加流式测试;当流式 span 除 token 指标外还记录 gen_ai.usage.reasoning_tokens 时,即表示完成。issue 作者表示愿意提交 PR,但没有报告负责人或关联的 pull request。
由索引模型根据 Issue 内容生成。
描述
Which component is this bug for?
OpenAI Instrumentation
📜 Description
A streamed chat completion never gets gen_ai.usage.reasoning_tokens, even when its usage chunk carries completion_tokens_details.reasoning_tokens. Without stream=True the span records it.
Only _handle_response sets the attribute (shared/chat_wrappers.py:334-354 at 8d9c93f), since #3336. Every stream path, async included, goes through _set_streaming_token_metrics (chat_wrappers.py:615), which sets input and output tokens and nothing else. The semantic-conventions page defines it as the reasoning part of completion_tokens, with no exception for streams. The only test, test_chat_reasoning (tests/traces/test_chat.py:1449), makes a non-stream call.
👟 Reproduction steps
- At
8d9c93f:pip install -e packages/opentelemetry-semantic-conventions-ai -e packages/opentelemetry-instrumentation-openai openai==3.35.1 opentelemetry-sdk. - Run this (a mock transport, no network):
import json
import httpx
import openai
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
exporter = InMemorySpanExporter()
provider = TracerProvider()
provider.add_span_processor(SimpleSpanProcessor(exporter))
OpenAIInstrumentor().instrument(tracer_provider=provider)
USAGE = {"prompt_tokens": 12, "completion_tokens": 300, "total_tokens": 312,
"completion_tokens_details": {"reasoning_tokens": 256}}
BASE = {"id": "c1", "created": 0, "model": "o4-mini"}
def handler(request):
if json.loads(request.content).get("stream"):
chunks = [
BASE | {"object": "chat.completion.chunk", "choices": [{"index": 0, "delta": {
"role": "assistant", "content": "Paris."}, "finish_reason": "stop"}]},
BASE | {"object": "chat.completion.chunk", "choices": [], "usage": USAGE},
]
body = "".join(f"data: {json.dumps(c)}\n\n" for c in chunks) + "data: [DONE]\n\n"
return httpx.Response(200, content=body.encode(),
headers={"content-type": "text/event-stream"})
return httpx.Response(200, json=BASE | {"object": "chat.completion", "usage": USAGE,
"choices": [{"index": 0, "message": {"role": "assistant", "content": "Paris."},
"finish_reason": "stop"}]})
client = openai.OpenAI(api_key="x", http_client=httpx.Client(transport=httpx.MockTransport(handler)))
for stream in (False, True):
kw = {"stream_options": {"include_usage": True}} if stream else {}
resp = client.chat.completions.create(model="o4-mini", stream=stream,
messages=[{"role": "user", "content": "Capital of France?"}], **kw)
if stream:
for _ in resp:
pass
a = exporter.get_finished_spans()[-1].attributes
print(f"stream={stream!s:<5} output_tokens={a.get('gen_ai.usage.output_tokens')} "
f"reasoning_tokens={a.get('gen_ai.usage.reasoning_tokens')}")
exporter.clear()
👍 Expected behavior
Both spans carry gen_ai.usage.reasoning_tokens=256.
👎 Actual Behavior with Screenshots
$ python repro_openai.py
stream=False output_tokens=300 reasoning_tokens=256
stream=True output_tokens=300 reasoning_tokens=None
🤖 Python Version
3.12
📃 Provide any additional context for the Bug.
I ran the sync stream only, and read the async path from the code.
👀 Have you spent some time to check if this bug has been raised before?
- I checked and didn't find similar issue
- Searched open and closed issues and pull requests for
reasoning_tokensandreasoning streaming. #4458, #4461 and #4462 cover Anthropic, #4488 covers Groq. No open pull request addsreasoningtochat_wrappers.py.
- Searched open and closed issues and pull requests for
Are you willing to submit PR?
Yes I am willing to submit a PR!
@doronkopit5, I'd move the reasoning block into a helper that _handle_response and _set_streaming_token_metrics both call, so every stream path gets it, plus a streamed twin of test_chat_reasoning. Shall I open it?
- 主要语言
- Python
- 星标
- 7.5k
- 派生
- 1.2k
- 平均合并
- 2 天 6 小时
- 30 天内合并 PR
- 2
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
traceloop/openllmetry 的其他 Issue
-
bug python
难度 2/5 1-3 小时 新手友好度 76/100
traceloop/openllmetry#4717 ·
维护者通常 1 天内回复
-
🐛 Bug Report: Incomplete cache token migration after #4243 breaks Bedrock and Groq instrumentation可能已有人在做 @Quantum-Enigma-dot 于 21 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 76/100
traceloop/openllmetry#4665 · 1 条评论 ·
维护者通常 1 天内回复
-
Bug Report: Failed dataset deletes still remove local rows and columns可能已有人在做 @inchang-ing 于 32 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 88/100
traceloop/openllmetry#4630 ·
维护者通常 1 天内回复
-
🐛 Bug Report: LiteLLM instrumentation does not record seed, stop, frequency_penalty, presence_penalty可能已有人在做 @shantam77 于 38 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 85/100
traceloop/openllmetry#4598 · 2 条评论 ·
维护者通常 1 天内回复
-
🐛 Bug Report: LiteLLM instrumentation never ends the span when a call is interrupted (KeyboardInterrupt, asyncio cancellation)可能已有人在做 @rupak-eng 于 39 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 80/100
traceloop/openllmetry#4597 · 1 条评论 ·
维护者通常 1 天内回复
查看 traceloop/openllmetry 的全部 Issue
相似的 Issue
-
Internal Error未关闭bug
难度 2/5 1-3 小时 新手友好度 66/100
frappe/frappe_docker#2071 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
The-Pocket/PocketFlow#161 ·
-
comp/desktop P2 type/bug
难度 2/5 1-3 小时 新手友好度 78/100
NousResearch/hermes-agent#157702 ·
维护者通常 1 天内回复
-
scibench_physics / scibench_chemistry: a correct answer scores 0 when the unit has a power of ten可能已有人在做 @BahaaMattar 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 84/100
EvolvingLMMs-Lab/lmms-eval#1699 ·
维护者通常 1 天内回复
-
project_inputs.html uses undefined file variable for dropdown IDs, lacks visual tag badges, and has empty delete labels可能已有人在做 @Rucha0901 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 82/100
aboutcode-org/scancode.io#2354 ·
维护者通常 1 天内回复