1. 错误信息
在使用 Openai Agents SDK时，报错如下，
Tracing client error 403: {"error":{"code":"unsupported_country_region_territory","message":"Country, region, or territory not supported","param":null,"type":"request_forbidden"}}
2. 原因
Agents SDK 默认开启了 Tracing，会调用 https://api.openai.com/v1/traces/ingest 这个 api 上传 Trace。
2025-03-19 20:46:13 DEBUG [_trace.py:47] connect_tcp.started host='api.openai.com' port=443 local_address=None timeout=5.0 socket_options=None
2025-03-19 20:46:13 DEBUG [_trace.py:47] connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7a35cfcf8220>
2025-03-19 20:46:13 DEBUG [_trace.py:47] start_tls.started ssl_context=<ssl.SSLContext object at 0x7a35cda61b40> server_hostname='api.openai.com' timeout=5.0
2025-03-19 20:46:13 DEBUG [_trace.py:47] start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7a35cfcf81f0>
2025-03-19 20:46:13 DEBUG [_trace.py:47] send_request_headers.started request=<Request [b'POST']>
2025-03-19 20:46:13 DEBUG [_trace.py:47] send_request_headers.complete
2025-03-19 20:46:13 DEBUG [_trace.py:47] send_request_body.started request=<Request [b'POST']>
2025-03-19 20:46:13 DEBUG [_trace.py:47] send_request_body.complete
2025-03-19 20:46:13 DEBUG [_trace.py:47] receive_response_headers.started request=<Request [b'POST']>
2025-03-19 20:46:13 DEBUG [_trace.py:47] receive_response_headers.complete return_value=(b'HTTP/1.1', 403, b'Forbidden', [(b'Date', b'Wed, 19 Mar 2025 12:46:15 GMT'), (b'Content-Type', b'application/json'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Vary', b'Accept-Encoding'), (b'Strict-Transport-Security', b'max-age=31536000; includeSubDomains; preload'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'922d1250ce9f332a-HKG'), (b'Content-Encoding', b'gzip'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-03-19 20:46:13 INFO [_client.py:1025] HTTP Request: POST https://api.openai.com/v1/traces/ingest "HTTP/1.1 403 Forbidden"
2025-03-19 20:46:13 DEBUG [_trace.py:47] receive_response_body.started request=<Request [b'POST']>
2025-03-19 20:46:13 DEBUG [_trace.py:47] receive_response_body.complete
2025-03-19 20:46:13 DEBUG [_trace.py:47] response_closed.started
2025-03-19 20:46:13 DEBUG [_trace.py:47] response_closed.complete
Tracing client error 403: {"error":{"code":"unsupported_country_region_territory","message":"Country, region, or territory not supported","param":null,"type":"request_forbidden"}}
3. 解决方法
方法一：
设置环境变量 OPENAI_AGENTS_DISABLE_TRACING=1
方法二：
设置 agents.run.RunConfig.tracing_disabled 为 True，
result = Runner.run_sync(
agent,
"写一段编程中递归的代码示例。",
run_config=RunConfig(tracing_disabled=False),
)
方法三：
使用 LangSmith，
安装 “langsmith[openai-agents]”，
pip install "langsmith[openai-agents]"
示例代码，
import os
import asyncio
from agents import Agent, Runner, set_trace_processors
from langsmith.wrappers import OpenAIAgentsTracingProcessor
os.environ["LANGSMITH_API_KEY"] = "lsv2_pt_******"
os.environ["LANGSMITH_ENDPOINT"] = "https://api.smith.langchain.com"
async def main():
agent = Agent(
name="Captain Obvious",
instructions="You are Captain Obvious, the world's most literal technical support agent.",
)
question = "Why is my code failing when I try to divide by zero? I keep getting this error message."
result = await Runner.run(agent, question)
print(result.final_output)
if __name__ == "__main__":
set_trace_processors([OpenAIAgentsTracingProcessor()])
asyncio.run(main())
之后可以在 LangSmith 平台查看 Trace，
方法四：
在 方法三： 的基础上，引入LangFuse，
不先改成使用 LangSmith，还是会调用
https://api.openai.com/v1/traces/ingest这个 api 上传 Trace。
安装依赖，
pip install openai-agents
pip install nest_asyncio
pip install pydantic-ai[logfire]
设置环境变量和 LangFuse 认证信息，
import os
import base64
# Replace with your Langfuse keys.
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..."
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..."
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # or 'https://us.cloud.langfuse.com'
# Build Basic Auth header.
LANGFUSE_AUTH = base64.b64encode(
f"{os.environ.get('LANGFUSE_PUBLIC_KEY')}:{os.environ.get('LANGFUSE_SECRET_KEY')}".encode()
).decode()
# Configure OpenTelemetry endpoint & headers
os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = os.environ.get("LANGFUSE_HOST") + "/api/public/otel"
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
Instrumenting the Agent，
import nest_asyncio
nest_asyncio.apply()
import logfire
# Configure logfire instrumentation.
logfire.configure(
service_name='my_agent_service',
send_to_logfire=False,
)
# This method automatically patches the OpenAI Agents SDK to send logs via OTLP to Langfuse.
logfire.instrument_openai_agents()
示例，
import asyncio
from agents import Agent, Runner
async def main():
agent = Agent(
name="Assistant",
instructions="You only respond in haikus.",
)
result = await Runner.run(agent, "Tell me about recursion in programming.")
print(result.final_output)
if __name__ == "__main__":
set_trace_processors([OpenAIAgentsTracingProcessor()])
asyncio.run(main())
这样的话，Trace 也会上传到 LangFuse。
参考资料：