Skip to content

chore: GenAI Client(evals) - fix single turn metrics on Agent Scraping CUJ #6439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
copybara-service merged 1 commit into from
Mar 18, 2026
Merged

chore: GenAI Client(evals) - fix single turn metrics on Agent Scraping CUJ #6439

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
157 changes: 149 additions & 8 deletions tests/unit/vertexai/genai/test_evals.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1313,6 +1313,31 @@ def test_run_inference_with_agent_engine_and_session_inputs_dict(
]
],
"response": ["agent response"],
"agent_data": [
{
"agents": None,
"turns": [
{
"events": [
{
"author": "model",
"content": {
"parts": [{"text": "intermediate1"}]
},
},
{
"author": "model",
"content": {
"parts": [{"text": "agent response"}]
},
},
],
"turn_id": "turn_0",
"turn_index": 0,
}
],
}
],
}
),
)
Expand Down Expand Up @@ -1392,6 +1417,31 @@ def test_run_inference_with_agent_engine_and_session_inputs_literal_string(
]
],
"response": ["agent response"],
"agent_data": [
{
"agents": None,
"turns": [
{
"events": [
{
"author": "model",
"content": {
"parts": [{"text": "intermediate1"}]
},
},
{
"author": "model",
"content": {
"parts": [{"text": "agent response"}]
},
},
],
"turn_id": "turn_0",
"turn_index": 0,
}
],
}
],
}
),
)
Expand Down Expand Up @@ -1571,6 +1621,72 @@ def run_async_side_effect(*args, **kwargs):
],
],
"response": ["agent response", "agent response 2"],
"agent_data": [
{
"agents": {
"mock_agent": {
"agent_id": "mock_agent",
"agent_resource_name": None,
"agent_type": "Mock",
"instruction": "mock instruction",
"description": "mock description",
"tools": [],
}
},
"turns": [
{
"events": [
{
"author": "model",
"content": {
"parts": [{"text": "intermediate1"}]
},
},
{
"author": "model",
"content": {
"parts": [{"text": "agent response"}]
},
},
],
"turn_id": "turn_0",
"turn_index": 0,
}
],
},
{
"agents": {
"mock_agent": {
"agent_id": "mock_agent",
"agent_resource_name": None,
"agent_type": "Mock",
"instruction": "mock instruction",
"description": "mock description",
"tools": [],
}
},
"turns": [
{
"events": [
{
"author": "model",
"content": {
"parts": [{"text": "intermediate2"}]
},
},
{
"author": "model",
"content": {
"parts": [{"text": "agent response 2"}]
},
},
],
"turn_id": "turn_0",
"turn_index": 0,
}
],
},
],
}
)
pd.testing.assert_frame_equal(
Expand Down Expand Up @@ -1952,6 +2068,31 @@ def test_run_agent_internal_success(self, mock_run_agent):
]
],
"response": ["final response"],
"agent_data": [
{
"agents": None,
"turns": [
{
"events": [
{
"author": "model",
"content": {
"parts": [{"text": "intermediate1"}]
},
},
{
"author": "model",
"content": {
"parts": [{"text": "final response"}]
},
},
],
"turn_id": "turn_0",
"turn_index": 0,
}
],
}
],
}
)
pd.testing.assert_frame_equal(result_df, expected_df)
Expand Down Expand Up @@ -2144,24 +2285,24 @@ def test_run_agent_internal_malformed_event(self, mock_run_agent):
assert not result_df["intermediate_events"][0]


class TestIsMultiTurnAgentRun:
"""Unit tests for the _is_multi_turn_agent_run function."""
class TestIsMultiTurnAgentSimulation:
"""Unit tests for the _is_multi_turn_agent_simulation function."""

def test_is_multi_turn_agent_run_with_config(self):
def test_is_multi_turn_agent_simulation_with_config(self):
config = vertexai_genai_types.evals.UserSimulatorConfig(model_name="gemini-pro")
assert _evals_common._is_multi_turn_agent_run(
assert _evals_common._is_multi_turn_agent_simulation(
user_simulator_config=config, prompt_dataset=pd.DataFrame()
)

def test_is_multi_turn_agent_run_with_conversation_plan(self):
def test_is_multi_turn_agent_simulation_with_conversation_plan(self):
prompt_dataset = pd.DataFrame({"conversation_plan": ["plan"]})
assert _evals_common._is_multi_turn_agent_run(
assert _evals_common._is_multi_turn_agent_simulation(
user_simulator_config=None, prompt_dataset=prompt_dataset
)

def test_is_multi_turn_agent_run_false(self):
def test_is_multi_turn_agent_simulation_false(self):
prompt_dataset = pd.DataFrame({"prompt": ["prompt"]})
assert not _evals_common._is_multi_turn_agent_run(
assert not _evals_common._is_multi_turn_agent_simulation(
user_simulator_config=None, prompt_dataset=prompt_dataset
)

Expand Down
Loading
Loading