xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-23 15:56:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BUGFIX] Mistral tool call parser v11+ (#30332)

Browse Source 
Signed-off-by: juliendenize <julien.denize@mistral.ai>
This commit is contained in:
Julien Denize 2025-12-09 15:55:38 +01:00 committed by GitHub
parent ee14644ba9
commit 5c213d2899
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 30 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
tests/tool_use/test_mistral_tool_parser.py
View File

@ -615,6 +615,7 @@ def test_extract_tool_calls_streaming(
"single_tool_weather",
"multiple_tool_calls",
"content_before_tool",
"complex",
],
argnames=["model_output", "expected_tool_calls", "expected_content"],
argvalues=[
@ -673,6 +674,21 @@ def test_extract_tool_calls_streaming(
],
"bla",
),
(
# Complex
"""[TOOL_CALLS]bash{"command": "print(\\"hello world!\\")\\nre.compile(r\'{}\')"}""", # noqa: E501
[
ToolCall(
function=FunctionCall(
name="bash",
arguments=json.dumps(
{"command": "print(\"hello world!\")\nre.compile(r'{}')"}
),
)
)
],
"",
),
],
)
def test_extract_tool_calls_streaming_one_chunk(

22
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py
View File

@ -99,12 +99,7 @@ class MistralToolParser(ToolParser):
self.bot_token = "[TOOL_CALLS]"
self.bot_token_id = self.vocab.get(self.bot_token)
self.tool_call_regex = re.compile(r"\[{.*}\]", re.DOTALL)
if not _is_pre_v11_tokeniser(self.model_tokenizer):
self.fn_name_regex = re.compile(
r"([a-zA-Z0-9_-]+)(\{[\s\S]*?\}+)", re.DOTALL
)
else:
self.fn_name_regex = None
self._is_pre_v11 = _is_pre_v11_tokeniser(self.model_tokenizer)
if self.bot_token_id is None:
raise RuntimeError(
@ -148,17 +143,18 @@ class MistralToolParser(ToolParser):
tool_content = model_output.replace(self.bot_token, "").strip()
try:
# we first try to directly load the json as parsing very nested
# jsons is difficult
try:
if self.fn_name_regex:
if not self._is_pre_v11:
function_call_arr = []
for single_tool_content in model_output.split(self.bot_token):
matches = self.fn_name_regex.findall(single_tool_content)
if "{" not in single_tool_content:
continue
for match in matches:
fn_name = match[0]
args = match[1]
end_name = single_tool_content.find("{")
fn_name, args = (
single_tool_content[:end_name],
single_tool_content[end_name:],
)
# fn_name is encoded outside serialized json dump
# only arguments are serialized