phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 04:45:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

more recordings

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-02 14:49:50 -07:00
parent b14a7c1b0f
commit 31f211f0ad
25 changed files with 2609 additions and 227 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/unit/providers/inference/test_remote_vllm.py
View file

@ -455,7 +455,7 @@ async def test_process_vllm_chat_completion_stream_response_tool_call_args_last_
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
assert chunks[-2].event.delta.type == "tool_call"
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments_str
async def test_process_vllm_chat_completion_stream_response_no_finish_reason():
@ -467,7 +467,7 @@ async def test_process_vllm_chat_completion_stream_response_no_finish_reason():
mock_tool_name = "mock_tool"
mock_tool_arguments = {"arg1": 0, "arg2": 100}
mock_tool_arguments_str = '"{\\"arg1\\": 0, \\"arg2\\": 100}"'
mock_tool_arguments_str = json.dumps(mock_tool_arguments)
async def mock_stream():
mock_chunks = [
@ -507,7 +507,7 @@ async def test_process_vllm_chat_completion_stream_response_no_finish_reason():
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
assert chunks[-2].event.delta.type == "tool_call"
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments_str
async def test_process_vllm_chat_completion_stream_response_tool_without_args():
@ -555,7 +555,7 @@ async def test_process_vllm_chat_completion_stream_response_tool_without_args():
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
assert chunks[-2].event.delta.type == "tool_call"
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
assert chunks[-2].event.delta.tool_call.arguments == {}
assert chunks[-2].event.delta.tool_call.arguments == "{}"
async def test_health_status_success(vllm_inference_adapter):