academic-research agent giving "ERROR - init.py:157 - Failed to detach context" #305
Description
academic-research agent is not working after summarizing the pdf. Giving this error:
2025-08-10 15:42:31,678 - WARNING - types.py:5259 - Warning: there are non-text parts in the response: ['thought_signature'], returning concatenated text result from text parts. Check the full candidates.content.parts accessor to get the full model response.
INFO: 49.43.202.223:0 - "GET /apps/academic_research/users/user/sessions/59a74048-450f-4279-8125-8e4c9a5782c7 HTTP/1.1" 200 OK
INFO: 49.43.202.223:0 - "GET /debug/trace/session/59a74048-450f-4279-8125-8e4c9a5782c7 HTTP/1.1" 200 OK
INFO: 49.43.202.223:0 - "POST /run_sse HTTP/1.1" 200 OK
2025-08-10 15:42:39,471 - INFO - envs.py:47 - Loaded .env file for academic_research at /workspaces/adk-samples/python/agents/academic-research/academic_research/.env
2025-08-10 15:42:39,517 - INFO - google_llm.py:111 - Sending out request, model: gemini-2.5-flash, backend: GoogleLLMVariant.VERTEX_AI, stream: False
2025-08-10 15:42:39,517 - INFO - models.py:7804 - AFC is enabled with max remote calls: 10.
2025-08-10 15:42:54,119 - INFO - _client.py:1740 - HTTP Request: POST https://us-central1-aiplatform.googleapis.com/v1beta1/projects/no-research/locations/us-central1/publishers/google/models/gemini-2.5-flash:generateContent "HTTP/1.1 200 OK"
2025-08-10 15:42:54,121 - INFO - google_llm.py:203 - Response received from the model.
2025-08-10 15:42:54,121 - WARNING - types.py:5259 - Warning: there are non-text parts in the response: ['thought_signature', 'function_call'], returning concatenated text result from text parts. Check the full candidates.content.parts accessor to get the full model response.
2025-08-10 15:42:54,171 - INFO - google_llm.py:111 - Sending out request, model: gemini-2.5-flash, backend: GoogleLLMVariant.VERTEX_AI, stream: False
2025-08-10 15:42:54,171 - INFO - models.py:7804 - AFC is enabled with max remote calls: 10.
build graph
INFO: 49.43.202.223:0 - "GET /apps/academic_research/users/user/sessions/59a74048-450f-4279-8125-8e4c9a5782c7/events/32895ace-4dc3-4dc0-9c28-bff9abae079c/graph HTTP/1.1" 200 OK
INFO: 49.43.202.223:0 - "GET /debug/trace/32895ace-4dc3-4dc0-9c28-bff9abae079c HTTP/1.1" 404 Not Found
build graph
INFO: 49.43.202.223:0 - "GET /apps/academic_research/users/user/sessions/59a74048-450f-4279-8125-8e4c9a5782c7/events/5c9900bf-f07a-4aa8-9a48-fbc6522db0b0/graph HTTP/1.1" 200 OK
INFO: 49.43.202.223:0 - "GET /debug/trace/5c9900bf-f07a-4aa8-9a48-fbc6522db0b0 HTTP/1.1" 200 OK
2025-08-10 15:43:39,467 - ERROR - init.py:157 - Failed to detach context
Traceback (most recent call last):
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/opentelemetry/trace/init.py", line 589, in use_span
yield span
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/opentelemetry/sdk/trace/init.py", line 1105, in start_as_current_span
yield span
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/opentelemetry/trace/init.py", line 454, in start_as_current_span
yield span
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/google/adk/flows/llm_flows/base_llm_flow.py", line 629, in _call_llm_async
yield llm_response
GeneratorExit
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/opentelemetry/context/init.py", line 155, in detach
_RUNTIME_CONTEXT.detach(token)
File "/home/codespace/.cache/pypoetry/virtualenvs/academic-research-cgAc3NVp-py3.12/lib/python3.12/site-packages/opentelemetry/context/contextvars_context.py", line 53, in detach
self._current_context.reset(token)
ValueError: <Token var=<ContextVar name='current_context' default={} at 0x761e17a37ab0> at 0x761e0fed69c0> was created in a different Context