Test chat with tools: 1. spliced_message (after chat_template) contains tool-related content 2. Model output contains tool_call
(self)
| 64 | self.assertEqual(outputs[-1].num_cached_tokens, 64) |
| 65 | |
| 66 | def test_chat_with_tools(self): |
| 67 | """Test chat with tools: |
| 68 | 1. spliced_message (after chat_template) contains tool-related content |
| 69 | 2. Model output contains tool_call |
| 70 | """ |
| 71 | prompts = [{"role": "user", "content": "北京海淀区今天天气怎么样?用摄氏度表示温度。"}] |
| 72 | tools = [ |
| 73 | { |
| 74 | "type": "function", |
| 75 | "function": { |
| 76 | "name": "get_weather", |
| 77 | "description": "Determine weather in my location", |
| 78 | "parameters": { |
| 79 | "type": "object", |
| 80 | "properties": { |
| 81 | "location": {"type": "string", "description": "The city and state e.g. San Francisco, CA"}, |
| 82 | "unit": {"type": "string", "enum": ["c", "f"]}, |
| 83 | }, |
| 84 | "additionalProperties": False, |
| 85 | "required": ["location", "unit"], |
| 86 | }, |
| 87 | "strict": True, |
| 88 | }, |
| 89 | } |
| 90 | ] |
| 91 | chat_template = "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}" |
| 92 | |
| 93 | data_processor = self.llm.llm_engine.data_processor |
| 94 | captured_spliced_message = None |
| 95 | |
| 96 | def capture_spliced_message(request_or_messages, **kwargs): |
| 97 | """Wrap original messages2ids to capture spliced_message""" |
| 98 | token_ids = data_processor.original_messages2ids(request_or_messages, **kwargs) |
| 99 | nonlocal captured_spliced_message |
| 100 | captured_spliced_message = request_or_messages.get("prompt_tokens") |
| 101 | return token_ids |
| 102 | |
| 103 | data_processor.original_messages2ids = data_processor.messages2ids |
| 104 | data_processor.messages2ids = capture_spliced_message |
| 105 | |
| 106 | try: |
| 107 | outputs = self.llm.chat( |
| 108 | messages=prompts, |
| 109 | tools=tools, |
| 110 | chat_template=chat_template, |
| 111 | chat_template_kwargs={"enable_thinking": False}, |
| 112 | stream=False, |
| 113 | ) |
| 114 | |
| 115 | self.assertIsNotNone(captured_spliced_message, "Failed to capture spliced_message from messages2ids") |
| 116 | self.assertIn( |
| 117 | "<tools>", |
| 118 | captured_spliced_message, |
| 119 | f"spliced_message '{captured_spliced_message}' missing <tools> tag (chat_template not applied)", |
| 120 | ) |
| 121 | |
| 122 | output = outputs[0] |
| 123 | self.assertEqual(len(prompts), len(outputs)) |