forked from phoenix-oss/llama-stack-mirror
6378c2a2f3
# What does this PR do? When the result of a ToolCall gets passed back into vLLM for the model to handle the tool call result (as is often the case in agentic tool-calling workflows), we forgot to handle the case where BuiltinTool calls are not string values but instead instances of the BuiltinTool enum. This fixes that, properly converting those enums to string values before trying to serialize them into an OpenAI chat completion request to vLLM. PR #1931 fixed a bug where we weren't passing these tool calling results back into vLLM, but as a side-effect it created this serialization bug when using BuiltinTools. Closes #2070 ## Test Plan I added a new unit test to the openai_compat unit tests to cover this scenario, ensured the new test failed before this fix, and all the existing tests there plus the new one passed with this fix. ``` python -m pytest -s -v tests/unit/providers/utils/inference/test_openai_compat.py ``` Signed-off-by: Ben Browning <bbrownin@redhat.com>
69 lines
2.3 KiB
Python
69 lines
2.3 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.common.content_types import TextContentItem
|
|
from llama_stack.apis.inference.inference import CompletionMessage, UserMessage
|
|
from llama_stack.models.llama.datatypes import BuiltinTool, StopReason, ToolCall
|
|
from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_convert_message_to_openai_dict():
|
|
message = UserMessage(content=[TextContentItem(text="Hello, world!")], role="user")
|
|
assert await convert_message_to_openai_dict(message) == {
|
|
"role": "user",
|
|
"content": [{"type": "text", "text": "Hello, world!"}],
|
|
}
|
|
|
|
|
|
# Test convert_message_to_openai_dict with a tool call
|
|
@pytest.mark.asyncio
|
|
async def test_convert_message_to_openai_dict_with_tool_call():
|
|
message = CompletionMessage(
|
|
content="",
|
|
tool_calls=[
|
|
ToolCall(call_id="123", tool_name="test_tool", arguments_json='{"foo": "bar"}', arguments={"foo": "bar"})
|
|
],
|
|
stop_reason=StopReason.end_of_turn,
|
|
)
|
|
|
|
openai_dict = await convert_message_to_openai_dict(message)
|
|
|
|
assert openai_dict == {
|
|
"role": "assistant",
|
|
"content": [{"type": "text", "text": ""}],
|
|
"tool_calls": [
|
|
{"id": "123", "type": "function", "function": {"name": "test_tool", "arguments": '{"foo": "bar"}'}}
|
|
],
|
|
}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_convert_message_to_openai_dict_with_builtin_tool_call():
|
|
message = CompletionMessage(
|
|
content="",
|
|
tool_calls=[
|
|
ToolCall(
|
|
call_id="123",
|
|
tool_name=BuiltinTool.brave_search,
|
|
arguments_json='{"foo": "bar"}',
|
|
arguments={"foo": "bar"},
|
|
)
|
|
],
|
|
stop_reason=StopReason.end_of_turn,
|
|
)
|
|
|
|
openai_dict = await convert_message_to_openai_dict(message)
|
|
|
|
assert openai_dict == {
|
|
"role": "assistant",
|
|
"content": [{"type": "text", "text": ""}],
|
|
"tool_calls": [
|
|
{"id": "123", "type": "function", "function": {"name": "brave_search", "arguments": '{"foo": "bar"}'}}
|
|
],
|
|
}
|