[mohitdixit02]

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: Runner.run_async runs an LlmAgent with neither new_message nor invocation_id instead of raising ValueError #7934

Problem:
Runner.run_async documents:
Raises: ValueError: If the session is not found; If both invocation_id and new_message are None.

However, when the root agent is an LlmAgent or a BaseNode, run_async branched into _run_node_async() and returned before reaching the validation check in _run_with_trace. As a result, calling run_async with new_message=None and invocation_id=None ran without error and called the model with empty contents ([[]]).

Solution:
Enforced the if not invocation_id and new_message is None: check at the entry of Runner.run_async before delegating to _run_node_async or _run_with_trace.
This ensures all root agent types (LlmAgent, BaseNode, and BaseAgent) uniformly validate the arguments and raise ValueError as documented.

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

Summary of passed pytest results:

pytest tests/unittests/test_runners.py -k "test_run_async_llm_agent_without_message_or_invocation_id_raises_value_error or
test_run_async_base_node_without_message_or_invocation_id_raises_value_error or test_run_async_applies_state_delta_when_resuming_without_new_message"

collected 238 items / 234 deselected / 4 selected
tests/unittests/test_runners.py ....                                     [100%]
====================== 4 passed, 234 deselected in 6.03s ======================

Manual End-to-End (E2E) Tests:

Verified against the reproduction script in #7934 with an LlmAgent and a recording model:

runner = Runner(app_name="demo", agent=LlmAgent(name="greeter", model=Recorder()), session_service=InMemorySessionService())
await runner.session_service.create_session(app_name="demo", user_id="u", session_id="s")
events = [event async for event in runner.run_async(user_id="u", session_id="s", new_message=None)]

• Before: Executed model call with empty contents (events: 1, model calls: [[]]).
• After: Raises ValueError: Running an agent requires either a new_message or an invocation_id to resume a previous invocation. Session: s, User: u.

Checklist

• I have read the CONTRIBUTING.md https://github.com/google/adk-python/blob/main/CONTRIBUTING.md document.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.