Repository navigation
Description
🔴 Required Information
Describe the Bug:
When the agent run raises, A2aAgentExecutor.execute ends the task with a TASK_STATE_FAILED status whose message is str(e) (make_text_part(str(e)) in a2a/executor/a2a_agent_executor.py, and the same line in a2a_agent_executor_impl.py). Whatever the exception says goes to the A2A caller verbatim.
Some exceptions say a lot. LiteLLM's APIConnectionError, for one, embeds the Python traceback in its message, so the caller receives the server's file paths:
litellm.APIConnectionError: litellm.APIError: LiteLLM: provider returned a response with no 'choices'. ...
Traceback (most recent call last):
File "<server venv>/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 900, in acompletion
final_response_obj = convert_to_model_response_object(
...
When the caller is an ADK RemoteA2aAgent, that text then reaches the calling agent's event stream as a plain text part (#6708), so its end user reads it as the agent's answer. That is how we found it: a user of one of our agents got the traceback above as a reply.
The server already logs the exception with exc_info=True on the line before, so the caller does not need the detail.
Steps to Reproduce:
pip install "google-adk[a2a]==2.11.0" "a2a-sdk[http-server]==1.2.1"- Run the script below. It serves an ADK
A2aAgentExecutorin process overhttpx.ASGITransport, with a model that raises, and sends oneSendMessage. It needs no network or credentials.
repro.py
"""What an A2A caller receives when the served ADK agent's run raises."""
import asyncio
import json
import logging
import warnings
import httpx
from a2a.server.request_handlers import DefaultRequestHandler
from a2a.server.routes import add_a2a_routes_to_fastapi, create_jsonrpc_routes
from a2a.server.tasks import InMemoryTaskStore
from a2a.types import AgentCapabilities, AgentCard, AgentInterface
from fastapi import FastAPI
from google.adk.a2a.executor.a2a_agent_executor import A2aAgentExecutor
from google.adk.agents import LlmAgent
from google.adk.models.base_llm import BaseLlm
from google.adk.runners import Runner
from google.adk.sessions import InMemorySessionService
warnings.filterwarnings("ignore")
logging.disable(logging.CRITICAL)
class FailingModel(BaseLlm): # stands in for a provider error
async def generate_content_async(self, llm_request, stream=False):
raise RuntimeError(
"provider rejected the call: Traceback (most recent call last):\n"
' File "/srv/agent/.venv/lib/python3.12/site-packages/provider/client.py", line 900'
)
yield
async def main():
card = AgentCard(
name="agent",
description="agent",
version="1",
capabilities=AgentCapabilities(streaming=True),
default_input_modes=["text/plain"],
default_output_modes=["text/plain"],
supported_interfaces=[
AgentInterface(url="http://agent.test/a2a", protocol_binding="JSONRPC")
],
)
agent = LlmAgent(name="agent", model=FailingModel(model="fake"), instruction="x")
executor = A2aAgentExecutor(
runner=Runner(
app_name="app",
agent=agent,
session_service=InMemorySessionService(),
auto_create_session=True,
)
)
app = FastAPI()
add_a2a_routes_to_fastapi(
app,
jsonrpc_routes=create_jsonrpc_routes(
DefaultRequestHandler(executor, InMemoryTaskStore(), card), rpc_url="/a2a"
),
)
async with httpx.AsyncClient(
transport=httpx.ASGITransport(app=app), base_url="http://agent.test"
) as client:
response = await client.post(
"/a2a",
headers={"A2A-Version": "1.0"},
json={
"jsonrpc": "2.0",
"id": 1,
"method": "SendMessage",
"params": {
"message": {
"messageId": "m1",
"role": "ROLE_USER",
"parts": [{"text": "hello"}],
}
},
},
)
status = response.json()["result"]["task"]["status"]
print(json.dumps(status, indent=2))
asyncio.run(main())Expected Behavior:
The failed status carries a generic message, or one the server chooses, and the exception's details stay in the server's log. ADK already has a path for a chosen message: convert_event_to_a2a_events turns an event with error_code into a TASK_STATE_FAILED status carrying the event's error_message, or DEFAULT_ERROR_MESSAGE. Only an exception that escapes the run takes the str(e) path.
Observed Behavior:
{
"state": "TASK_STATE_FAILED",
"message": {
"messageId": "5f89d64d-db72-4846-a968-c014801f3870",
"role": "ROLE_AGENT",
"parts": [
{
"text": "provider rejected the call: Traceback (most recent call last):\n File \"/srv/agent/.venv/lib/python3.12/site-packages/provider/client.py\", line 900"
}
]
},
"timestamp": "2026-10-02T20:45:29.502125Z"
}Environment Details:
- ADK Library Version (pip show google-adk): 2.11.0, with a2a-sdk 1.2.1. Both
make_text_part(str(e))lines are unchanged onmain. - Desktop OS: macOS
- Python Version (python -V): 3.12.12
Model Information:
- Are you using LiteLLM: Yes in production, where the exception came from. No in the reproduction, which uses a
BaseLlmthat raises. - Which model is being used: Gemini through a LiteLLM proxy in production, N/A for the reproduction.
🟡 Optional Information
Regression:
Not known.
Related:
- Follow-up to #4309: fix for failed A2A tasks needs both _handle_a2a_response/_v2, _compat.TS_FAILED, and error_code — still reproducible in 2.6.2 #6708: on the client side,
RemoteA2aAgentpasses a failed task's status message on as ordinary content. RemoteA2aAgent(mode="task"): delegation to a non-ADK A2A agent never closes when the task ends inTASK_STATE_COMPLETED; the coordinator never gets its turn back #7248 / fix(a2a): close task-mode delegation when a plain A2A peer completes without finish_task #7251: on the client side, a failed task never closes a task-mode delegation.
Activity
Big-Marvel commentedon Oct 3, 2026
Hi, is this issue still open for contributions? If so, I would love to work on this
@GWeale
fix(a2a): sanitize error message on executor failure to prevent data …
fix(a2a): sanitize error message on executor failure to prevent data …
sanketpatil06 commentedon Oct 6, 2026
Hi @lamberttraccard,
Thanks for the detailed report. We have reproduced the issue on our end.
A2aAgentExecutorbuilds theTASK_STATE_FAILEDmessage fromstr(e), so the raw exception text reaches the A2A caller.#7402 replaces this with the generic
DEFAULT_ERROR_MESSAGE, and the full exception is still logged on the server. Could you check whether it resolves the issue on your end?lamberttraccard commentedon Oct 21, 2026
Thanks. I ran the repro from the report against the #7402 branch: the failed status now carries "An error occurred during processing" instead of the exception text, where 2.11.0 still returns the traceback. That resolves the leak we hit. The client-side half, where
RemoteA2aAgentshows a failed task's message as the agent's answer, is still #6708.lamberttraccard commentedon Nov 3, 2026
@sanketpatil06 I answered above on Oct 21: #7402 fixes the leak on our side, so nothing is pending from me. Could you remove the
request clarificationlabel and get #7402 reviewed 🙏 ?