From 8c6daf6e2fe8b8e731866700719741def43ca165 Mon Sep 17 00:00:00 2001 From: Flora Feng <4florafeng@gmail.com> Date: Fri, 29 May 2026 18:52:46 -0400 Subject: [PATCH] [CI] Remove duplicate Harmony test coverage (#44023) Signed-off-by: sfeng33 <4florafeng@gmail.com> --- .../chat_completion/test_serving_chat.py | 85 ------------------- .../test_serving_chat_stream_harmony.py | 79 ++--------------- 2 files changed, 8 insertions(+), 156 deletions(-) diff --git a/tests/entrypoints/openai/chat_completion/test_serving_chat.py b/tests/entrypoints/openai/chat_completion/test_serving_chat.py index 45fae821af..11793ac8f4 100644 --- a/tests/entrypoints/openai/chat_completion/test_serving_chat.py +++ b/tests/entrypoints/openai/chat_completion/test_serving_chat.py @@ -1449,91 +1449,6 @@ class TestServingChatWithHarmony: ], ) - @pytest.mark.asyncio - async def test_tools_and_reasoning( - self, serving_chat, stream, weather_tools, weather_messages_start - ): - tools = weather_tools - messages = list(weather_messages_start) - - # Test the Harmony messages for the first turn's input - req = ChatCompletionRequest(model=MODEL_NAME, messages=messages, tools=tools) - input_messages, _ = ( - serving_chat.openai_serving_render._make_request_with_harmony(req) - ) - verify_harmony_messages( - input_messages, - [ - {"role": "system"}, - {"role": "developer", "tool_definitions": ["get_weather"]}, - {"role": "user", "content": messages[0]["content"]}, - ], - ) - - # Test the Chat Completion response for the first turn's output - reasoning_str = "I'll call get_weather." - tool_args_str = '{"location": "Paris"}' - response_str = ( - f"<|channel|>analysis<|message|>{reasoning_str}<|end|>" - "<|start|>assistant to=functions.get_weather<|channel|>commentary" - f"<|constrain|>json<|message|>{tool_args_str}<|call|>" - ) - response = await self.generate_response_from_harmony_str( - serving_chat, req, response_str, stream=stream - ) - verify_chat_response( - response, - reasoning=reasoning_str, - tool_calls=[("get_weather", tool_args_str)], - ) - - tool_call = response.choices[0].message.tool_calls[0] - - # Add the output messages from the first turn as input to the second turn - for choice in response.choices: - messages.append(choice.message.model_dump(exclude_none=True)) - - # Add our tool output message - messages.append( - { - "role": "tool", - "tool_call_id": tool_call.id, - "content": "20 degrees Celsius", - }, - ) - - # Test the Harmony messages for the second turn's input - req_2 = ChatCompletionRequest(model=MODEL_NAME, messages=messages, tools=tools) - input_messages_2, _ = ( - serving_chat.openai_serving_render._make_request_with_harmony(req_2) - ) - verify_harmony_messages( - input_messages_2, - [ - {"role": "system"}, - {"role": "developer"}, - {"role": "user"}, - { - "role": "assistant", - "channel": "analysis", - "content": reasoning_str, - }, - { - "role": "assistant", - "channel": "commentary", - "recipient": "functions.get_weather", - "content": tool_args_str, - }, - { - "role": "tool", - "author_name": "functions.get_weather", - "channel": "commentary", - "recipient": "assistant", - "content": "20 degrees Celsius", - }, - ], - ) - @pytest.mark.asyncio async def test_multi_turn_tools_and_reasoning( self, serving_chat, stream, weather_tools, weather_messages_start diff --git a/tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py b/tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py index 0a0802a793..1c058adaf0 100644 --- a/tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py +++ b/tests/entrypoints/openai/chat_completion/test_serving_chat_stream_harmony.py @@ -121,7 +121,9 @@ class TestExtractHarmonyStreamingDelta: token_states = [ TokenState( - channel=channel, recipient="functions.get_weather", text=args_text + channel=channel, + recipient="functions.get_weather", + text=args_text, ) ] @@ -168,7 +170,11 @@ class TestExtractHarmonyStreamingDelta: parser = MockStreamableParser(messages=messages) token_states = [ - TokenState(channel="commentary", recipient="functions.tool2", text="args") + TokenState( + channel="commentary", + recipient="functions.tool2", + text="args", + ) ] delta_message, _ = extract_harmony_streaming_delta( @@ -199,75 +205,6 @@ class TestExtractHarmonyStreamingDelta: assert delta_message.content == delta_text assert tools_streamed is False - @pytest.mark.parametrize("channel", ["commentary", "analysis"]) - @patch("vllm.entrypoints.openai.chat_completion.stream_harmony.make_tool_call_id") - def test_new_tool_call_without_functions_prefix( - self, mock_make_tool_call_id, channel - ): - mock_make_tool_call_id.return_value = "call_bare123" - parser = MockStreamableParser() - - token_states = [TokenState(channel=channel, recipient="get_weather", text="")] - - delta_message, tools_streamed = extract_harmony_streaming_delta( - harmony_parser=parser, - token_states=token_states, - prev_recipient=None, - include_reasoning=False, - ) - - assert delta_message is not None - assert len(delta_message.tool_calls) == 1 - tool_call = delta_message.tool_calls[0] - assert tool_call.id == "call_bare123" - assert tool_call.type == "function" - assert tool_call.function.name == "get_weather" - assert tool_call.function.arguments == "" - assert tool_call.index == 0 - assert tools_streamed is True - - @pytest.mark.parametrize("channel", ["commentary", "analysis"]) - def test_tool_call_argument_streaming_without_functions_prefix(self, channel): - parser = MockStreamableParser() - args_text = '{"location": "Paris"}' - - token_states = [ - TokenState(channel=channel, recipient="get_weather", text=args_text) - ] - - delta_message, tools_streamed = extract_harmony_streaming_delta( - harmony_parser=parser, - token_states=token_states, - prev_recipient="get_weather", - include_reasoning=False, - ) - - assert delta_message is not None - tool_call = delta_message.tool_calls[0] - assert tool_call.id is None - assert tool_call.function.arguments == args_text - assert tool_call.index == 0 - assert tools_streamed is True - - def test_tool_call_index_from_previous_messages_without_functions_prefix(self): - messages = [ - MockMessage(channel="commentary", recipient="tool1"), - ] - parser = MockStreamableParser(messages=messages) - - token_states = [ - TokenState(channel="commentary", recipient="tool2", text="args") - ] - - delta_message, _ = extract_harmony_streaming_delta( - harmony_parser=parser, - token_states=token_states, - prev_recipient="tool2", - include_reasoning=False, - ) - - assert delta_message.tool_calls[0].index == 1 - @pytest.mark.parametrize("channel", ["commentary", "analysis"]) @patch("vllm.entrypoints.openai.chat_completion.stream_harmony.make_tool_call_id") def test_new_tool_call_dotted_function_name(self, mock_make_tool_call_id, channel):