mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-14 17:16:09 +00:00
# What does this PR do? previously, developers who ran `./scripts/unit-tests.sh` would get `asyncio-mode=auto`, which meant `@pytest.mark.asyncio` and `@pytest_asyncio.fixture` were redundent. developers who ran `pytest` directly would get pytest's default (strict mode), would run into errors leading them to add `@pytest.mark.asyncio` / `@pytest_asyncio.fixture` to their code. with this change - - `asyncio_mode=auto` is included in `pyproject.toml` making behavior consistent for all invocations of pytest - removes all redundant `@pytest_asyncio.fixture` and `@pytest.mark.asyncio` - for good measure, requires `pytest>=8.4` and `pytest-asyncio>=1.0` ## Test Plan - `./scripts/unit-tests.sh` - `uv run pytest tests/unit`
116 lines
3.7 KiB
Python
116 lines
3.7 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
|
|
from llama_stack.apis.agents import AgentConfig, Turn
|
|
from llama_stack.apis.inference import SamplingParams, UserMessage
|
|
from llama_stack.providers.datatypes import Api
|
|
from llama_stack.providers.utils.kvstore import kvstore_impl
|
|
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_messages():
|
|
return [
|
|
UserMessage(content="What's the weather like today?"),
|
|
]
|
|
|
|
|
|
def pick_inference_model(inference_model):
|
|
return inference_model
|
|
|
|
|
|
def create_agent_session(agents_impl, agent_config):
|
|
return agents_impl.create_agent_session(agent_config)
|
|
|
|
|
|
@pytest.fixture
|
|
def common_params(inference_model):
|
|
inference_model = pick_inference_model(inference_model)
|
|
|
|
return dict(
|
|
model=inference_model,
|
|
instructions="You are a helpful assistant.",
|
|
enable_session_persistence=True,
|
|
sampling_params=SamplingParams(temperature=0.7, top_p=0.95),
|
|
input_shields=[],
|
|
output_shields=[],
|
|
tools=[],
|
|
max_infer_iters=5,
|
|
)
|
|
|
|
|
|
@pytest.mark.skip(reason="This test needs to be migrated to api / client-sdk world")
|
|
async def test_delete_agents_and_sessions(self, agents_stack, common_params):
|
|
agents_impl = agents_stack.impls[Api.agents]
|
|
agent_id, session_id = await create_agent_session(
|
|
agents_impl,
|
|
AgentConfig(
|
|
**{
|
|
**common_params,
|
|
"input_shields": [],
|
|
"output_shields": [],
|
|
}
|
|
),
|
|
)
|
|
|
|
run_config = agents_stack.run_config
|
|
provider_config = run_config.providers["agents"][0].config
|
|
persistence_store = await kvstore_impl(SqliteKVStoreConfig(**provider_config["persistence_store"]))
|
|
|
|
await agents_impl.delete_agents_session(agent_id, session_id)
|
|
session_response = await persistence_store.get(f"session:{agent_id}:{session_id}")
|
|
|
|
await agents_impl.delete_agents(agent_id)
|
|
agent_response = await persistence_store.get(f"agent:{agent_id}")
|
|
|
|
assert session_response is None
|
|
assert agent_response is None
|
|
|
|
|
|
@pytest.mark.skip(reason="This test needs to be migrated to api / client-sdk world")
|
|
async def test_get_agent_turns_and_steps(self, agents_stack, sample_messages, common_params):
|
|
agents_impl = agents_stack.impls[Api.agents]
|
|
|
|
agent_id, session_id = await create_agent_session(
|
|
agents_impl,
|
|
AgentConfig(
|
|
**{
|
|
**common_params,
|
|
"input_shields": [],
|
|
"output_shields": [],
|
|
}
|
|
),
|
|
)
|
|
|
|
# Create and execute a turn
|
|
turn_request = dict(
|
|
agent_id=agent_id,
|
|
session_id=session_id,
|
|
messages=sample_messages,
|
|
stream=True,
|
|
)
|
|
|
|
turn_response = [chunk async for chunk in await agents_impl.create_agent_turn(**turn_request)]
|
|
|
|
final_event = turn_response[-1].event.payload
|
|
turn_id = final_event.turn.turn_id
|
|
|
|
provider_config = agents_stack.run_config.providers["agents"][0].config
|
|
persistence_store = await kvstore_impl(SqliteKVStoreConfig(**provider_config["persistence_store"]))
|
|
turn = await persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
|
|
response = await agents_impl.get_agents_turn(agent_id, session_id, turn_id)
|
|
|
|
assert isinstance(response, Turn)
|
|
assert response == final_event.turn
|
|
assert turn == final_event.turn.model_dump_json()
|
|
|
|
steps = final_event.turn.steps
|
|
step_id = steps[0].step_id
|
|
step_response = await agents_impl.get_agents_step(agent_id, session_id, turn_id, step_id)
|
|
|
|
assert step_response.step == steps[0]
|