to_a2a(Workflow) fails when Workflow contains LlmAgent with input_schema/output_schema (ADK 2.0.0b1)

[gorgonline]

Environment

• google-adk==2.0.0b1
• Python 3.13, macOS

Description

Calling to_a2a(workflow) on a Workflow whose nodes include an LlmAgent with input_schema or output_schema fails in two distinct ways:

Bug 1 — AgentCardBuilder requires sub_agents on Workflow.
AgentCardBuilder accesses Workflow.sub_agents, a BaseAgent field not exposed by Workflow. This raises RuntimeError on agent-card construction.

Bug 2 — Event converter cannot map Workflow events to A2A message parts.
If AgentCard is supplied manually (bypassing Bug 1), the A2A event converter does not translate Workflow node events into A2A message parts. The task stays in working state forever; the client never gets a final response.

Repro

from google.adk.workflow import Workflow
from google.adk.agents import LlmAgent
from google.adk.a2a.utils.agent_to_a2a import to_a2a
from pydantic import BaseModel

class Out(BaseModel):
    text: str

writer = LlmAgent(
    name="writer",
    model="gemini-2.5-flash",
    instruction="Write a short reply.",
    output_schema=Out,
)

wf = Workflow(name="pipe", edges=[("START", writer)])
app = to_a2a(wf)  # RuntimeError from AgentCardBuilder

Workaround

Wrap the Workflow in an LlmAgent:

wrapper = LlmAgent(
    name="pipe_a2a",
    model="gemini-2.5-flash",
    instruction="Delegate to the workflow.",
    sub_agents=[wf],
)
app = to_a2a(wrapper)

This avoids both bugs but adds an extra LlmAgent layer plus an extra LLM call per request. Schema-less Workflows work directly with to_a2a and do not need this wrapper.

Expected behavior

to_a2a(Workflow) should serve any Workflow — with or without schemas — as a first-class A2A agent, without requiring an LlmAgent wrapper.

Related

• Native support for sub_agents in A2A Remote Agents to eliminate "Agent Tool" wrapper redundancy #4065 — Native sub_agents support in A2A Remote Agents (same wrapper-redundancy theme from the consumer side)
• LongRunningFunctionTool + A2A Protocol Task Completion Issue #4145 — LongRunningFunctionTool + A2A task completion hanging in working (possibly same root cause as Bug 2 here)

[sanketpatil06]

Hi @gorgonline , Thanks for reporting this.
We have tested this out on ADK 2.0.0b1 and can confirm that passing a Workflow directly into to_a2a() currently throws an error. Regarding the workaround of wrapping the Workflow inside an LlmAgent's sub_agents, it appears this triggers a strict Pydantic ValidationError in standard environments.
Workaround:
the safest workaround if you need A2A right now is to serve the LlmAgent directly rather than placing it in a single-step workflow.

from google.adk.agents import LlmAgent
from google.adk.a2a.utils.agent_to_a2a import to_a2a
from pydantic import BaseModel

class Out(BaseModel):
    text: str

writer = LlmAgent(
    name="writer",
    model="gemini-2.5-flash",
    instruction="Write a short reply.",
    output_schema=Out,
)

# Pass the agent directly to A2A
app = to_a2a(writer)
root_agent = writer

[haranrk]

Hey @gorgonline! We don't support converting Workflows to a2a apps just yet, but we're working on it. In the meantime, the workaround you and @sanketpatil06 suggested is the best way to go!