Skip to content

GitLab

Unverified Commit 78683580 authored by Yiheng Xu's avatar Yiheng Xu Committed by GitHub
Browse files

[Bugfix]: Qwen3 Coder Tool Parser (#23099) 


Signed-off-by: default avatarYiheng Xu <charlesyihengxu@gmail.com>
Co-authored-by: default avatarAaron Pham <contact@aarnphm.xyz>
parent fecbb7c7
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 576 additions and 248 deletions
examples/tool_chat_template_qwen3coder.jinja 0 → 100644
View file @ 78683580
{% macro render_extra_keys(json_dict, handled_keys) %}
{%- if json_dict is mapping %}
{%- for json_key in json_dict if json_key not in handled_keys %}
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
{%- else %}
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
{%- endif %}
{%- endfor %}
{%- endif %}
{% endmacro %}
{%- if messages[0]["role"] == "system" %}
{%- set system_message = messages[0]["content"] %}
{%- set loop_messages = messages[1:] %}
{%- else %}
{%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = [] %}
{%- endif %}
{%- if system_message is defined %}
{{- "<|im_start|>system\n" + system_message }}
{%- else %}
{%- if tools is iterable and tools | length > 0 %}
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
{%- endif %}
{%- endif %}
{%- if tools is iterable and tools | length > 0 %}
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
{{- "<tools>" }}
{%- for tool in tools %}
{%- if tool.function is defined %}
{%- set tool = tool.function %}
{%- endif %}
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
{%- if tool.description is defined %}
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
{%- endif %}
{{- '\n<parameters>' }}
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
{%- for param_name, param_fields in tool.parameters.properties|items %}
{{- '\n<parameter>' }}
{{- '\n<name>' ~ param_name ~ '</name>' }}
{%- if param_fields.type is defined %}
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
{%- endif %}
{%- if param_fields.description is defined %}
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
{%- endif %}
{%- set handled_keys = ['name', 'type', 'description'] %}
{{- render_extra_keys(param_fields, handled_keys) }}
{{- '\n</parameter>' }}
{%- endfor %}
{%- endif %}
{% set handled_keys = ['type', 'properties'] %}
{{- render_extra_keys(tool.parameters, handled_keys) }}
{{- '\n</parameters>' }}
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
{{- render_extra_keys(tool, handled_keys) }}
{{- '\n</function>' }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- endif %}
{%- if system_message is defined %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if tools is iterable and tools | length > 0 %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in loop_messages %}
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
{{- '<|im_start|>' + message.role }}
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
{{- '\n' + message.content | trim + '\n' }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user\n' }}
{%- endif %}
{{- '<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>\n' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}
tests/tool_use/test_qwen3coder_tool_parser.py
View file @ 78683580
......@@ -16,7 +16,7 @@ from vllm.entrypoints.openai.tool_parsers.qwen3coder_tool_parser import (
from vllm.transformers_utils.detokenizer import detokenize_incrementally
from vllm.transformers_utils.tokenizer import AnyTokenizer, get_tokenizer
MODEL = "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
MODEL = "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
@pytest.fixture(scope="module")
......@@ -397,7 +397,9 @@ hello world
"no_tools",
"single_tool",
"single_tool_with_content",
"single_tool_multiline_param",
"parallel_tools",
"tool_with_typed_params", # Added this test case
],
argnames=["model_output", "expected_tool_calls", "expected_content"],
argvalues=[
......@@ -422,7 +424,7 @@ fahrenheit
"state": "TX",
"unit": "fahrenheit"
})))
], ""),
], None),
('''Sure! Let me check the weather for you.<tool_call>
<function=get_current_weather>
<parameter=city>
......@@ -445,6 +447,30 @@ fahrenheit
})))
], "Sure! Let me check the weather for you."),
('''<tool_call>
<function=calculate_area>
<parameter=shape>
rectangle
</parameter>
<parameter=dimensions>
{"width": 10,
"height": 20}
</parameter>
<parameter=precision>
2
</parameter>
</function>
</tool_call>''', [
ToolCall(function=FunctionCall(name="calculate_area",
arguments=json.dumps({
"shape": "rectangle",
"dimensions": {
"width": 10,
"height": 20
},
"precision": 2
})))
], None),
('''<tool_call>
<function=get_current_weather>
<parameter=city>
Dallas
......@@ -484,13 +510,36 @@ celsius
"state": "FL",
"unit": "celsius"
})))
], ""),
], None),
# Added tool_with_typed_params test case
('''Let me calculate that area for you.<tool_call>
<function=calculate_area>
<parameter=shape>
circle
</parameter>
<parameter=dimensions>
{"radius": 15.5}
</parameter>
<parameter=precision>
3
</parameter>
</function>
</tool_call>''', [
ToolCall(function=FunctionCall(name="calculate_area",
arguments=json.dumps({
"shape": "circle",
"dimensions": {
"radius": 15.5
},
"precision": 3
})))
], "Let me calculate that area for you."),
],
)
def test_extract_tool_calls_streaming(qwen3_tool_parser, qwen3_tokenizer,
sample_tools, model_output,
expected_tool_calls, expected_content):
"""Test incremental streaming behavior"""
"""Test incremental streaming behavior including typed parameters"""
request = ChatCompletionRequest(model=MODEL,
messages=[],
tools=sample_tools)
......@@ -539,7 +588,7 @@ def test_extract_tool_calls_streaming(qwen3_tool_parser, qwen3_tokenizer,
"arguments"] += tool_call.function.arguments
# Verify final content
assert other_content == expected_content
assert other_content == (expected_content or "") # Handle None case
# Verify we got all expected tool calls
assert len(tool_states) == len(expected_tool_calls)
......@@ -559,6 +608,125 @@ def test_extract_tool_calls_streaming(qwen3_tool_parser, qwen3_tokenizer,
assert actual_args == expected_args
def test_extract_tool_calls_missing_closing_parameter_tag(
qwen3_tool_parser, sample_tools):
"""Test handling of missing closing </parameter> tag"""
# Using get_current_weather from sample_tools but with malformed XML
model_output = '''Let me check the weather for you:
<tool_call>
<function=get_current_weather>
<parameter=city>
Dallas
<parameter=state>
TX
</parameter>
<parameter=unit>
fahrenheit
</parameter>
</function>
</tool_call>'''
request = ChatCompletionRequest(model=MODEL,
messages=[],
tools=sample_tools)
extracted_tool_calls = qwen3_tool_parser.extract_tool_calls(
model_output, request=request)
# The parser should handle the malformed XML gracefully
assert extracted_tool_calls.tools_called
assert len(extracted_tool_calls.tool_calls) == 1
# Verify the function name is correct
assert extracted_tool_calls.tool_calls[
0].function.name == "get_current_weather"
# Verify the arguments are parsed despite the missing closing tag
args = json.loads(extracted_tool_calls.tool_calls[0].function.arguments)
assert "city" in args
assert args["city"] == "Dallas"
assert args["state"] == "TX"
assert args["unit"] == "fahrenheit"
# Check that content before the tool call is preserved
assert "Let me check the weather for you:" in extracted_tool_calls.content
def test_extract_tool_calls_streaming_missing_closing_tag(
qwen3_tool_parser, qwen3_tokenizer, sample_tools):
"""Test streaming with missing closing </parameter> tag"""
# Using get_current_weather from sample_tools but with malformed XML
model_output = '''Let me check the weather for you:
<tool_call>
<function=get_current_weather>
<parameter=city>
Dallas
<parameter=state>
TX
</parameter>
<parameter=unit>
fahrenheit
</parameter>
</function>
</tool_call>'''
request = ChatCompletionRequest(model=MODEL,
messages=[],
tools=sample_tools)
other_content = ''
tool_states = {}
for delta_message in stream_delta_message_generator(
qwen3_tool_parser, qwen3_tokenizer, model_output, request):
if delta_message.content:
other_content += delta_message.content
if delta_message.tool_calls:
for tool_call in delta_message.tool_calls:
idx = tool_call.index
if idx not in tool_states:
tool_states[idx] = {
"id": None,
"name": None,
"arguments": "",
"type": None
}
if tool_call.id:
tool_states[idx]["id"] = tool_call.id
if tool_call.type:
assert tool_call.type == "function"
tool_states[idx]["type"] = tool_call.type
if tool_call.function:
if tool_call.function.name:
tool_states[idx]["name"] = tool_call.function.name
if tool_call.function.arguments is not None:
tool_states[idx][
"arguments"] += tool_call.function.arguments
# Verify content was streamed
assert "Let me check the weather for you:" in other_content
# Verify we got the tool call
assert len(tool_states) == 1
state = tool_states[0]
assert state["id"] is not None
assert state["type"] == "function"
assert state["name"] == "get_current_weather"
# Verify arguments were parsed correctly despite missing closing tag
assert state["arguments"] is not None
args = json.loads(state["arguments"])
assert args["city"] == "Dallas"
assert args["state"] == "TX"
assert args["unit"] == "fahrenheit"
def test_extract_tool_calls_streaming_incremental(qwen3_tool_parser,
qwen3_tokenizer,
sample_tools):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment