Skip to content

[Bugfix] Consistent ascii handling in tool parsers #17704

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 21, 2025
Merged

[Bugfix] Consistent ascii handling in tool parsers #17704

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9ba7250
Consistent ascii handling in llama tool parser
schoennenbeck May 6, 2025
bc20d9f
Fix other tool call parsers
schoennenbeck May 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,8 @@ def extract_tool_calls(
function=FunctionCall(
name=function_call["name"],
# function call args are JSON but as a string
arguments=json.dumps(function_call["arguments"]),
arguments=json.dumps(function_call["arguments"],
ensure_ascii=False),
),
) for function_call in raw_function_calls
]
Expand Down Expand Up @@ -166,7 +167,8 @@ def extract_tool_calls_streaming(
if self.current_tool_id >= 0:
cur_arguments = current_tool_call.get("arguments")
if cur_arguments:
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
argument_diff = cur_args_json[sent:]
Expand Down Expand Up @@ -218,15 +220,17 @@ def extract_tool_calls_streaming(
if cur_arguments:
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
prev_arguments = self.prev_tool_call_arr[
self.current_tool_id].get("arguments")

argument_diff = None
if is_complete[self.current_tool_id]:
argument_diff = cur_args_json[sent:]
elif prev_arguments:
prev_args_json = json.dumps(prev_arguments)
prev_args_json = json.dumps(prev_arguments,
ensure_ascii=False)
if cur_args_json != prev_args_json:

prefix = find_common_prefix(
Expand Down
12 changes: 8 additions & 4 deletions vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,8 @@ def extract_tool_calls(
function=FunctionCall(
name=function_call["name"],
# function call args are JSON but as a string
arguments=json.dumps(function_call["arguments"]),
arguments=json.dumps(function_call["arguments"],
ensure_ascii=False),
),
) for function_call in raw_function_calls
]
Expand Down Expand Up @@ -151,7 +152,8 @@ def extract_tool_calls_streaming(
if self.current_tool_id >= 0:
cur_arguments = current_tool_call.get("arguments")
if cur_arguments:
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
argument_diff = cur_args_json[sent:]
Expand Down Expand Up @@ -197,15 +199,17 @@ def extract_tool_calls_streaming(
if cur_arguments:
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
prev_arguments = self.prev_tool_call_arr[
self.current_tool_id].get("arguments")

argument_diff = None
if is_complete[self.current_tool_id]:
argument_diff = cur_args_json[sent:]
elif prev_arguments:
prev_args_json = json.dumps(prev_arguments)
prev_args_json = json.dumps(prev_arguments,
ensure_ascii=False)
if cur_args_json != prev_args_json:
prefix = find_common_prefix(
prev_args_json, cur_args_json)
Expand Down
12 changes: 8 additions & 4 deletions vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,8 @@ def extract_tool_calls_streaming(
delta = None
# first time to get parameters
elif cur_arguments and not prev_arguments:
cur_arguments_json = json.dumps(cur_arguments)
cur_arguments_json = json.dumps(cur_arguments,
ensure_ascii=False)

arguments_delta = cur_arguments_json[:cur_arguments_json.
index(delta_text) +
Expand All @@ -148,8 +149,10 @@ def extract_tool_calls_streaming(
self.current_tool_id] += arguments_delta
# both prev and cur parameters, send the increase parameters
elif cur_arguments and prev_arguments:
cur_args_json = json.dumps(cur_arguments)
prev_args_json = json.dumps(prev_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
prev_args_json = json.dumps(prev_arguments,
ensure_ascii=False)

argument_diff = extract_intermediate_diff(
cur_args_json, prev_args_json)
Expand Down Expand Up @@ -190,7 +193,8 @@ def extract_tool_calls(
action_dict = json.loads(action)
name, parameters = action_dict['name'], json.dumps(
action_dict.get('parameters', action_dict.get('arguments',
{})))
{})),
ensure_ascii=False)

if not tools or name not in [t.function.name for t in tools]:
ExtractedToolCallInformation(tools_called=False,
Expand Down
16 changes: 10 additions & 6 deletions vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,8 +96,9 @@ def extract_tool_calls(
function=FunctionCall(
name=function_call["name"],
# function call args are JSON but as a string
arguments=json.dumps(function_call["arguments"])))
for function_call in raw_function_calls
arguments=json.dumps(function_call["arguments"],
ensure_ascii=False),
)) for function_call in raw_function_calls
]

content = model_output[:model_output.
Expand Down Expand Up @@ -187,7 +188,7 @@ def extract_tool_calls_streaming(
diff: Union[str, None] = current_tool_call.get("arguments")

if diff:
diff = json.dumps(diff).replace(
diff = json.dumps(diff, ensure_ascii=False).replace(
self.streamed_args_for_tool[self.current_tool_id],
"")
delta = DeltaMessage(tool_calls=[
Expand Down Expand Up @@ -248,7 +249,8 @@ def extract_tool_calls_streaming(
"mid-arguments")
delta = None
elif cur_arguments and not prev_arguments:
cur_arguments_json = json.dumps(cur_arguments)
cur_arguments_json = json.dumps(cur_arguments,
ensure_ascii=False)
logger.debug("finding %s in %s", new_text,
cur_arguments_json)

Expand All @@ -267,8 +269,10 @@ def extract_tool_calls_streaming(
self.current_tool_id] += arguments_delta

elif cur_arguments and prev_arguments:
cur_args_json = json.dumps(cur_arguments)
prev_args_json = json.dumps(prev_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
prev_args_json = json.dumps(prev_arguments,
ensure_ascii=False)
logger.debug("Searching for diff between \n%s\n%s",
cur_args_json, prev_args_json)

Expand Down
12 changes: 8 additions & 4 deletions vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@ def extract_tool_calls(
# function call args are JSON but as a string
arguments=json.dumps(raw_function_call["arguments"] \
if "arguments" in raw_function_call \
else raw_function_call["parameters"])))
else raw_function_call["parameters"],
ensure_ascii=False)))
for raw_function_call in function_call_arr
]

Expand Down Expand Up @@ -174,7 +175,8 @@ def extract_tool_calls_streaming(
if self.current_tool_id >= 0:
cur_arguments = current_tool_call.get("arguments")
if cur_arguments:
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
argument_diff = cur_args_json[sent:]
Expand Down Expand Up @@ -226,15 +228,17 @@ def extract_tool_calls_streaming(
if cur_arguments:
sent = len(
self.streamed_args_for_tool[self.current_tool_id])
cur_args_json = json.dumps(cur_arguments)
cur_args_json = json.dumps(cur_arguments,
ensure_ascii=False)
prev_arguments = self.prev_tool_call_arr[
self.current_tool_id].get("arguments")

argument_diff = None
if is_complete[self.current_tool_id]:
argument_diff = cur_args_json[sent:]
elif prev_arguments:
prev_args_json = json.dumps(prev_arguments)
prev_args_json = json.dumps(prev_arguments,
ensure_ascii=False)
if cur_args_json != prev_args_json:

prefix = find_common_prefix(
Expand Down
9 changes: 5 additions & 4 deletions vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,10 +79,11 @@ def extract_tool_calls(
name=raw_function_call["name"],
# function call args are JSON but as a string
arguments=json.dumps(
raw_function_call["arguments"] if "arguments" in
raw_function_call else
raw_function_call["parameters"])))
for raw_function_call in function_call_arr
raw_function_call["arguments"]
if "arguments" in raw_function_call else
raw_function_call["parameters"],
ensure_ascii=False),
)) for raw_function_call in function_call_arr
]

# get any content before the tool call
Expand Down
9 changes: 6 additions & 3 deletions vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,9 +200,12 @@ def _handle_single_tool(call: ast.Call) -> ToolCall:
arguments = {}
for keyword in call.keywords:
arguments[keyword.arg] = _get_parameter_value(keyword.value)
return ToolCall(type="function",
function=FunctionCall(name=function_name,
arguments=json.dumps(arguments)))
return ToolCall(
type="function",
function=FunctionCall(name=function_name,
arguments=json.dumps(arguments,
ensure_ascii=False)),
)


def _make_valid_python(text: str) -> Union[tuple[str, str], None]:
Expand Down