8000 TypeError when using LongRunningFunctionTool: SerializationIterator is not JSON serializable during event DB insert · Issue #586 · google/adk-python · GitHub
[go: up one dir, main page]
Skip to content
TypeError when using LongRunningFunctionTool: SerializationIterator is not JSON serializable during event DB insert #586
New issue
New issue
Open
Feature
Open
TypeError when using LongRunningFunctionTool: SerializationIterator is not JSON serializable during event DB insert#586
Feature
Assignees
seanzhou1023
Labels
toolsIssues related to tools
Milestone
 
Feature Roadmap
@JoaoCampista

Description

@JoaoCampista
JoaoCampista
opened on May 6, 2025

⚠️ Please make sure you read the contribution guide and file the issues in the right place.
[Contribution guide.](https://google.github.io/adk-docs/contributing-guide/)

Describe the bug

When using a LongRunningFunctionTool with a generator (yielding incremental progress updates), the ADK framework attempts to serialize the generator object itself (SerializationIterator) into the database, causing a TypeError. This leads to a crash when committing the session event to a PostgreSQL database.

To Reproduce

Steps to reproduce the behavior:

  1. Define a generator function wrapped in LongRunningFunctionTool.
  2. Create an agent using LlmAgent.
  3. Serve the agent via FastAPI using get_fast_api_app.
  4. Set SESSION_DB_URL to a PostgreSQL RDS instance.
  5. Send a request that triggers the long-running tool (via /run_sse).
  6. Observe the logs — the generator object fails to serialize and causes a crash.

Expected behavior

Intermediate yields and final return values from the tool should be processed and saved as individual serialized FunctionResponse events. The tool's generator object (SerializationIterator) should not be serialized or stored directly in the database.

Screenshots

N/A — full log provided below.

Desktop (please complete the following information):

  • OS: Windows 11
  • Python version: Python 3.13
  • ADK version: Latest (as of May 2025)
  • DB: PostgreSQL RDS

Code (minimal reproducible example)

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.long_running_tool import LongRunningFunctionTool 
import time

def long_task(*args, **kwargs):
    yield {"status": "pending", "message": "Starting task..."}
    time.sleep(2)
    yield {"status": "pending", "progress": 50}
    time.sleep(4)
    return {"status": "completed", "result": "Final outcome"}

root_agent = LlmAgent(
    model="gemini-2.0-flash",
    name="ProposalsAgent",
    description="A nice assistante that call the long_task tool",
    tools=[LongRunningFunctionTool(long_task)],
)

main.py

from fastapi import FastAPI
from google.adk.cli.fast_api import get_fast_api_app
from dotenv import load_dotenv
import os

load_dotenv()

AGENT_DIR = os.getenv("AGENT_DIR")
SESSION_DB_URL = os.getenv("SESSION_DB_URL")

app: FastAPI = get_fast_api_app(
    agent_dir=AGENT_DIR,
    session_db_url=SESSION_DB_URL,
    allow_origins=["*"],
    web=True
)

Full Log Output

INFO:     127.0.0.1:56658 - "POST /run_sse HTTP/1.1" 200 OK
INFO:C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\cli\utils\envs.py:Loaded .env file for teste at C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.env
INFO:google.adk.sessions.database_session_service:Append event: content=Content(parts=[Part(video_metadata=None, thought=None, code_execution_result=None, executable_code=None, file_data=None, function_call=None, function_response=None, inline_data=None, text='chame a tool')], role='user') grounding_metadata=None partial=None turn_complete=None error_code=None error_message=None interrupted=None custom_metadata=None invocation_id='e-a5d0b5db-a4b2-490d-8d56-5a47112649c6' author='user' actions=EventActions(skip_summarization=None, state_delta={}, artifact_delta={}, transfer_to_agent=None, escalate=None, requested_auth_configs={}) long_running_tool_ids=None branch=None id='CVFoDJX1' timestamp=1746545843.645539 to session f61e7626-fa90-4969-96da-d0f621c055bc
INFO:google.adk.models.google_llm:Sending out request, model: gemini-2.0-flash, backend: ml_dev, stream: False
INFO:google.adk.models.google_llm:
LLM Request:
-----------------------------------------------------------
System Instruction:
You are an agent. Your internal name is "ProposalsAgent".

 The description about you is "A nice assistante that call the long_task tool"
-----------------------------------------------------------
Contents:
{"parts":[{"text":"chame a tool"}],"role":"user"}
-----------------------------------------------------------
Functions:
long_task: {} -> None
-----------------------------------------------------------

INFO:google_genai.models:AFC is enabled with max remote calls: 10.
INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent "HTTP/1.1 200 OK"
WARNING:google_genai.types:Warning: there are non-text parts in the response: ['function_call'],returning concatenated text result from text parts,check out the non text parts for full response from model.
INFO:google.adk.models.google_llm:
LLM Response:
-----------------------------------------------------------
Text:
None
-----------------------------------------------------------
Function calls:
name: long_task, args: {}
-----------------------------------------------------------
Raw response:
{"candidates":[{"content":{"parts":[{"function_call":{"args":{},"name":"long_task"}}],"role":"model"},"finish_reason":"STOP","avg_logprobs":-0.000011800671927630901}],"model_version":"gemini-2.0-flash","usage_metadata":{"candidates_token_count":3,"candidates_tokens_details":[{"modality":"TEXT","token_count":3}],"prompt_token_count":39,"prompt_tokens_details":[{"modality":"TEXT","token_count":39}],"total_token_count":42},"automatic_function_calling_history":[]}
-----------------------------------------------------------

INFO:google.adk.sessions.database_session_service:Append event: content=Content(parts=[Part(video_metadata=None, thought=None, code_execution_result=None, executable_code=None, file_data=None, function_call=FunctionCall(id='adk-95a62e89-3367-4eef-a308-ee64c156e256', args={}, name='long_task'), function_response=None, inline_data=None, text=None)], role='model') grounding_metadata=None partial=None turn_complete=None error_code=None error_message=None interrupted=None custom_metadata=None invocation_id='e-a5d0b5db-a4b2-490d-8d56-5a47112649c6' author='ProposalsAgent' actions=EventActions(skip_summarization=None, state_delta={}, artifact_delta={}, transfer_to_agent=None, escalate=None, requested_auth_configs={}) long_running_tool_ids={'adk-95a62e89-3367-4eef-a308-ee64c156e256'} branch=None id='jhonJAcn' timestamp=1746545845.252927 to session f61e7626-fa90-4969-96da-d0f621c055bc
INFO:google.adk.cli.fast_api:Generated event in agent run streaming: {"content":{"parts":[{"functionCall":{"id":"adk-95a62e89-3367-4eef-a308-ee64c156e256","args":{},"name":"long_task"}}],"role":"model"},"invocation_id":"e-a5d0b5db-a4b2-490d-8d56-5a47112649c6","author":"ProposalsAgent","actions":{"state_delta":{},"artifact_delta":{},"requested_auth_configs":{}},"long_running_tool_ids":["adk-95a62e89-3367-4eef-a308-ee64c156e256"],"id":"jhonJAcn","timestamp":1746545845.252927}
INFO:google.adk.sessions.database_session_service:Append event: content=Content(parts=[Part(video_metadata=None, thought=None, code_execution_result=None, executable_code=None, file_data=None, function_call=None, function_response=FunctionResponse(id='adk-95a62e89-3367-4eef-a308-ee64c156e256', name='long_task', response={'result': <generator object long_task at 0x000001E3D1246670>}), inline_data=None, text=None)], role='user') grounding_metadata=None partial=None turn_complete=None error_code=None error_message=None interrupted=None custom_metadata=None invocation_id='e-a5d0b5db-a4b2-490d-8d56-5a47112649c6' author='ProposalsAgent' actions=EventActions(skip_summarization=None, state_delta={}, artifact_delta={}, transfer_to_agent=None, escalate=None, requested_auth_configs={}) long_running_tool_ids=None branch=None id='9p63RdCQ' timestamp=1746545848.549715 to session f61e7626-fa90-4969-96da-d0f621c055bc
ERROR:google.adk.cli.fast_api:Error in event_generator: (builtins.TypeError) Object of type SerializationIterator is not JSON serializable
[SQL: INSERT INTO events (id, app_name, user_id, session_id, invocation_id, author, branch, timestamp, content, actions, long_running_tool_ids_json, grounding_metadata, partial, turn_complete, error_code, error_message, interrupted) VALUES (%(id)s, %(app_name)s, %(user_id)s, %(session_id)s, %(invocation_id)s, %(author)s, %(branch)s, %(timestamp)s, %(content)s::JSONB, %(actions)s, %(long_running_tool_ids_json)s, %(grounding_metadata)s::JSONB, %(partial)s, %(turn_complete)s, %(error_code)s, %(error_message)s, %(interrupted)s)]
[parameters: [{'content': {'parts': [{'function_response': {'id': 'adk-95a62e89-3367-4eef-a308-ee64c156e256', 'name': 'long_task', 'response': {'result': Serializat ... (551 characters truncated) ... ing_tool_ids_json': None, 'interrupted': None, 'partial': None, 'turn_complete': None, 'grounding_metadata': None, 'error_code': None, 'branch': None}]]
Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 1812, in _execute_context
    context = constructor(
        dialect, self, conn, execution_options, *args, **kw
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\default.py", line 1521, in _init_compiled
    flattened_processors[key](compiled_params[key])
    ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\sql\type_api.py", line 2096, in process
    return fixed_impl_processor(
        fixed_process_param(value, dialect)
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\sql\sqltypes.py", line 2779, in process
    return json_serializer(value)
  File "C:\Python313\Lib\json\__init__.py", line 231, in dumps
    return _default_encoder.encode(obj)
           ~~~~~~~~~~~~~~~~~~~~~~~^^^^^
  File "C:\Python313\Lib\json\encoder.py", line 200, in encode
    chunks = self.iterencode(o, _one_shot=True)
  File "C:\Python313\Lib\json\encoder.py", line 261, in iterencode
    return _iterencode(o, 0)
  File "C:\Python313\Lib\json\encoder.py", line 180, in default
    raise TypeError(f'Object of type {o.__class__.__name__} '
                    f'is not JSON serializable')
TypeError: Object of type SerializationIterator is not JSON serializable

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\cli\fast_api.py", line 626, in event_generator
    async for event in runner.run_async(
    ...<8 lines>...
      yield f"data: {sse_event}\n\n"
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\runners.py", line 199, in run_async
    self.session_service.append_event(session=session, event=event)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\sessions\database_session_service.py", line 548, in append_event 
    sessionFactory.commit()
    ~~~~~~~~~~~~~~~~~~~~~^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 2032, in commit
    trans.commit(_to_root=True)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^
  File "<string>", line 2, in commit
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\state_changes.py", line 139, in _go
    ret_value = fn(self, *arg, **kw)
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 1313, in commit
    self._prepare_impl()
    ~~~~~~~~~~~~~~~~~~^^
  File "<string>", line 2, in _prepare_impl
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\state_changes.py", line 139, in _go
    ret_value = fn(self, *arg, **kw)
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 1288, in _prepare_impl
    self.session.flush()
    ~~~~~~~~~~~~~~~~~~^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 4353, in flush
    self._flush(objects)
    ~~~~~~~~~~~^^^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 4488, in _flush
    with util.safe_reraise():
         ~~~~~~~~~~~~~~~~~^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\util\langhelpers.py", line 146, in __exit__
    raise exc_value.with_traceback(exc_tb)
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\session.py", line 4449, in _flush
    flush_context.execute()
    ~~~~~~~~~~~~~~~~~~~~~^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\unitofwork.py", line 466, in execute
    rec.execute(self)
    ~~~~~~~~~~~^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\unitofwork.py", line 642, in execute
    util.preloaded.orm_persistence.save_obj(
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        self.mapper,
        ^^^^^^^^^^^^
        uow.states_for_mapper_hierarchy(self.mapper, False, False),
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
        uow,
        ^^^^
    )
    ^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\persistence.py", line 93, in save_obj
    _emit_insert_statements(
    ~~~~~~~~~~~~~~~~~~~~~~~^
        base_mapper,
        ^^^^^^^^^^^^
    ...<3 lines>...
        insert,
        ^^^^^^^
    )
    ^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\orm\persistence.py", line 1048, in _emit_insert_statements       
    result = connection.execute(
        statement, multiparams, execution_options=execution_options
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 1416, in execute
    return meth(
        self,
        distilled_parameters,
        execution_options or NO_OPTIONS,
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\sql\elements.py", line 523, in _execute_on_connection
    return connection._execute_clauseelement(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        self, distilled_params, execution_options
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 1638, in _execute_clauseelement
    ret = self._execute_context(
        dialect,
    ...<8 lines>...
        cache_hit=cache_hit,
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 1818, in _execute_context
    self._handle_dbapi_exception(
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        e, str(statement), parameters, None, None
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 2352, in _handle_dbapi_exception
    raise sqlalchemy_exception.with_traceback(exc_info[2]) from e
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\base.py", line 1812, in _execute_context
    context = constructor(
        dialect, self, conn, execution_options, *args, **kw
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\engine\default.py", line 1521, in _init_compiled
    flattened_processors[key](compiled_params[key])
    ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\sql\type_api.py", line 2096, in process
    return fixed_impl_processor(
        fixed_process_param(value, dialect)
    )
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\sqlalchemy\sql\sqltypes.py", line 2779, in process
    return json_serializer(value)
  File "C:\Python313\Lib\json\__init__.py", line 231, in dumps
    return _default_encoder.encode(obj)
           ~~~~~~~~~~~~~~~~~~~~~~~^^^^^
  File "C:\Python313\Lib\json\encoder.py", line 200, in encode
    chunks = self.iterencode(o, _one_shot=True)
  File "C:\Python313\Lib\json\encoder.py", line 261, in iterencode
    return _iterencode(o, 0)
  File "C:\Python313\Lib\json\encoder.py", line 180, in default
    raise TypeError(f'Object of type {o.__class__.__name__} '
                    f'is not JSON serializable')
sqlalchemy.exc.StatementError: (builtins.TypeError) Object of type SerializationIterator is not JSON serializable
[SQL: INSERT INTO events (id, app_name, user_id, session_id, invocation_id, author, branch, timestamp, content, actions, long_running_tool_ids_json, grounding_metadata, partial, turn_complete, error_code, error_message, interrupted) VALUES (%(id)s, %(app_name)s, %(user_id)s, %(session_id)s, %(invocation_id)s, %(author)s, %(branch)s, %(timestamp)s, %(content)s::JSONB, %(actions)s, %(long_running_tool_ids_json)s, %(grounding_metadata)s::JSONB, %(partial)s, %(turn_complete)s, %(error_code)s, %(error_message)s, %(interrupted)s)]
[parameters: [{'content': {'parts': [{'function_response': {'id': 'adk-95a62e89-3367-4eef-a308-ee64c156e256', 'name': 'long_task', 'response': {'result': Serializat ... (551 characters truncated) ... ing_tool_ids_json': None, 'interrupted': None, 'partial': None, 'turn_complete': None, 'grounding_metadata': None, 'error_code': None, 'branch': None}]]
ERROR:opentelemetry.context:Failed to detach context
Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 587, in use_span
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\sdk\trace\__init__.py", line 1105, in start_as_current_span   
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 452, in start_as_current_span        
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\agents\base_agent.py", line 128, in run_async
    yield event
GeneratorExit

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\context\__init__.py", line 155, in detach
    _RUNTIME_CONTEXT.detach(token)
    ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\context\contextvars_context.py", line 53, in detach
    self._current_context.reset(token)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
    _RUNTIME_CONTEXT.detach(token)
    ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\context\contextvars_context.py", line 53, in detach
    self._current_context.reset(token)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
    ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\context\contextvars_context.py", line 53, in detach
    self._current_context.reset(token)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
    self._current_context.reset(token)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
ValueError: <Token var=<ContextVar name='current_context' default={} at 0x000001E3C38CA610> at 0x000001E3D0238080> was created in a different Context
ERROR:opentelemetry.context:Failed to detach context
ValueError: <Token var=<ContextVar name='current_context' default={} at 0x000001E3C38CA610> at 0x000001E3D0238080> was created in a different Context
ERROR:opentelemetry.context:Failed to detach context
Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 587, in use_span
Traceback (most recent call last):
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 587, in use_span
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\sdk\trace\__init__.py", line 1105, in start_as_current_span   
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\sdk\trace\__init__.py", line 1105, in start_as_current_span   
    yield span
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 452, in start_as_current_span        
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\trace\__init__.py", line 452, in start_as_current_span        
    yield span
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\flows\llm_flows\base_llm_flow.py", line 487, in _call_llm_async  
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\google\adk\flows\llm_flows\base_llm_flow.py", line 487, in _call_llm_async  
    yield llm_response
    yield llm_response
GeneratorExit
GeneratorExit

During handling of the above exception, another exception occurred:

  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\site-packages\opentelemetry\context\__init__.py", line 155, in detach
    _RUNTIME_CONTEXT.detach(token)
    ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^
  File "C:\Users\JoaoC\Nextcloud\Projetos\Lugui\Agents\ai-ecs-agents\.venv\Lib\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 0x000001E3C38CA610> at 0x000001E3D023A600> was created in a different Context

Additional context

The error seems to occur specifically when the framework attempts to insert the function response (which contains a generator) into the events table of the session database. The ADK is passing a SerializationIterator (a generator object) directly inside the response.result field of a FunctionResponse, which is not JSON serializable.

This suggests that instead of serializing and storing each yielded result from the tool incrementally, the full generator is being included in the database payload. This causes a TypeError during the SQLAlchemy .commit() operation:

TypeError: Object of type SerializationIterator is not JSON serializable

The stack trace points to this during an INSERT INTO events (...) VALUES (...) SQL command.

This likely needs to be handled either by:

  • Consuming and serializing the generator before persisting the event; or
  • Updating the ADK's internal serialization logic to properly handle streamed results from LongRunningFunctionTool.

Metadata

Metadata

Assignees

Labels

toolsIssues related to tools

Type

Projects

No projects

Milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions
    0